remove print

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

.github/ISSUE_TEMPLATE/remote-vae-pilot-feedback.yml

@@ -1,38 +0,0 @@
-name: "\U0001F31F Remote VAE"
-description: Feedback for remote VAE pilot
-labels: [ "Remote VAE" ]
-
-body:
-  - type: textarea
-    id: positive
-    validations:
-      required: true
-    attributes:
-      label: Did you like the remote VAE solution?
-      description: |
-        If you liked it, we would appreciate it if you could elaborate what you liked.
-
-  - type: textarea
-    id: feedback
-    validations:
-      required: true
-    attributes:
-      label: What can be improved about the current solution?
-      description: |
-        Let us know the things you would like to see improved. Note that we will work optimizing the solution once the pilot is over and we have usage.
-
-  - type: textarea
-    id: others
-    validations:
-      required: true
-    attributes:
-      label: What other VAEs you would like to see if the pilot goes well?
-      description: |
-        Provide a list of the VAEs you would like to see in the future if the pilot goes well.
-
-  - type: textarea
-    id: additional-info
-    attributes:
-      label: Notify the members of the team
-      description: |
-        Tag the following folks when submitting this feedback: @hlky @sayakpaul

.github/workflows/benchmark.yml

@@ -23,7 +23,7 @@ jobs:
     runs-on:
       group: aws-g6-4xlarge-plus
     container:
-      image: diffusers/diffusers-pytorch-cuda
+      image: diffusers/diffusers-pytorch-compile-cuda
       options: --shm-size "16gb" --ipc host --gpus 0
     steps:
       - name: Checkout diffusers
@@ -38,7 +38,6 @@ jobs:
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install pandas peft
-          python -m uv pip uninstall transformers && python -m uv pip install transformers==4.48.0
       - name: Environment
         run: |
           python utils/print_env.py

.github/workflows/build_docker_images.yml

@@ -34,20 +34,13 @@ jobs:
         id: file_changes
         uses: jitterbit/get-changed-files@v1
         with:
-          format: "space-delimited"
+          format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Changed Docker Images
-        env: 
-          CHANGED_FILES: ${{ steps.file_changes.outputs.all }}
         run: |
-          echo "$CHANGED_FILES"
-          for FILE in $CHANGED_FILES; do 
-            # skip anything that isn't still on disk
-            if [[ ! -f "$FILE" ]]; then
-              echo "Skipping removed file $FILE"
-              continue
-            fi           
+          CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
+          for FILE in $CHANGED_FILES; do
             if [[ "$FILE" == docker/*Dockerfile ]]; then
               DOCKER_PATH="${FILE%/Dockerfile}"
               DOCKER_TAG=$(basename "$DOCKER_PATH")
@@ -72,9 +65,8 @@ jobs:
         image-name:
           - diffusers-pytorch-cpu
           - diffusers-pytorch-cuda
-          - diffusers-pytorch-cuda
+          - diffusers-pytorch-compile-cuda
           - diffusers-pytorch-xformers-cuda
-          - diffusers-pytorch-minimum-cuda
           - diffusers-flax-cpu
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu

.github/workflows/nightly_tests.yml

@@ -13,9 +13,8 @@ env:
   PYTEST_TIMEOUT: 600
   RUN_SLOW: yes
   RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 0
+  PIPELINE_USAGE_CUTOFF: 5000
   SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
-  CONSOLIDATED_REPORT_PATH: consolidated_test_report.md
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
@@ -100,6 +99,11 @@ jobs:
         with:
           name: pipeline_${{ matrix.module }}_test_reports
           path: reports
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_for_other_torch_modules:
     name: Nightly Torch CUDA Tests
@@ -170,48 +174,11 @@ jobs:
         name: torch_${{ matrix.module }}_cuda_test_reports
         path: reports
 
-  run_torch_compile_tests:
-    name: PyTorch Compile CUDA tests
-
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
+    - name: Generate Report and Notify Channel
+      if: always()
       run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
-    - name: Environment
-      run: |
-        python utils/print_env.py
-    - name: Run torch compile tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        RUN_COMPILE: yes
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: cat reports/tests_torch_compile_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_compile_test_reports
-        path: reports
+        pip install slack_sdk tabulate
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_big_gpu_torch_tests:
     name: Torch tests on big GPU
@@ -263,63 +230,67 @@ jobs:
         with:
           name: torch_cuda_big_gpu_test_reports
           path: reports
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+
+  run_flax_tpu_tests:
+    name: Nightly Flax TPU Tests
+    runs-on: docker-tpu
+    if: github.event_name == 'schedule'
 
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
     container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
+      image: diffusers/diffusers-flax-tpu
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash
     steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
 
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install pytest-reportlog
 
-      - name: Environment
-        run: |
-          python utils/print_env.py
+    - name: Environment
+      run: python utils/print_env.py
 
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_version_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
+    - name: Run nightly Flax TPU tests
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+      run: |
+        python -m pytest -n 0 \
+          -s -v -k "Flax" \
+          --make-reports=tests_flax_tpu \
+          --report-log=tests_flax_tpu.log \
+          tests/
 
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_flax_tpu_stats.txt
+        cat reports/tests_flax_tpu_failures_short.txt
 
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: flax_tpu_test_reports
+        path: reports
+
+    - name: Generate Report and Notify Channel
+      if: always()
+      run: |
+        pip install slack_sdk tabulate
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
@@ -370,25 +341,21 @@ jobs:
         name: tests_onnx_cuda_reports
         path: reports
 
+    - name: Generate Report and Notify Channel
+      if: always()
+      run: |
+        pip install slack_sdk tabulate
+        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+
   run_nightly_quantization_tests:
     name: Torch quantization nightly tests
     strategy:
       fail-fast: false
       max-parallel: 2
-      matrix:
+      matrix: 
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
-            additional_deps: ["peft"]
-          - backend: "gguf"
-            test_location: "gguf"
-            additional_deps: ["peft"]
-          - backend: "torchao"
-            test_location: "torchao"
-            additional_deps: []
-          - backend: "optimum_quanto"
-            test_location: "quanto"
-            additional_deps: []
     runs-on:
       group: aws-g6e-xlarge-plus
     container:
@@ -406,9 +373,6 @@ jobs:
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
           python -m uv pip install -U ${{ matrix.config.backend }}
-          if [ "${{ join(matrix.config.additional_deps, ' ') }}" != "" ]; then
-              python -m uv pip install ${{ join(matrix.config.additional_deps, ' ') }}
-          fi
           python -m uv pip install pytest-reportlog
       - name: Environment
         run: |
@@ -435,165 +399,11 @@ jobs:
         with:
           name: torch_cuda_${{ matrix.config.backend }}_reports
           path: reports
-          
-  run_nightly_pipeline_level_quantization_tests:
-    name: Torch quantization nightly tests
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-    runs-on:
-      group: aws-g6e-xlarge-plus
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus 0
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
-      - name: Install dependencies
+      - name: Generate Report and Notify Channel
+        if: always()
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install -U bitsandbytes optimum_quanto
-          python -m uv pip install pytest-reportlog
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Pipeline-level quantization tests on GPU
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-          BIG_GPU_MEMORY: 40
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            --make-reports=tests_pipeline_level_quant_torch_cuda \
-            --report-log=tests_pipeline_level_quant_torch_cuda.log \
-            tests/quantization/test_pipeline_level_quantization.py
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_level_quant_torch_cuda_stats.txt
-          cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_cuda_pipeline_level_quant_reports
-          path: reports
-
-  run_flax_tpu_tests:
-    name: Nightly Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
-    if: github.event_name == 'schedule'
-
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_flax_tpu_stats.txt
-        cat reports/tests_flax_tpu_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-  generate_consolidated_report:
-    name: Generate Consolidated Test Report
-    needs: [
-      run_nightly_tests_for_torch_pipelines,
-      run_nightly_tests_for_other_torch_modules,
-      run_torch_compile_tests,
-      run_big_gpu_torch_tests,
-      run_nightly_quantization_tests,
-      run_nightly_pipeline_level_quantization_tests,
-      run_nightly_onnx_tests,
-      torch_minimum_version_cuda_tests,
-      run_flax_tpu_tests
-    ]
-    if: always()
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Create reports directory
-        run: mkdir -p combined_reports
-
-      - name: Download all test reports
-        uses: actions/download-artifact@v4
-        with:
-          path: artifacts
-
-      - name: Prepare reports
-        run: |
-          # Move all report files to a single directory for processing
-          find artifacts -name "*.txt" -exec cp {} combined_reports/ \;
-
-      - name: Install dependencies
-        run: |
-          pip install -e .[test]
           pip install slack_sdk tabulate
-
-      - name: Generate consolidated report
-        run: |
-          python utils/consolidated_test_report.py \
-            --reports_dir combined_reports \
-            --output_file $CONSOLIDATED_REPORT_PATH \
-            --slack_channel_name diffusers-ci-nightly
-
-      - name: Show consolidated report
-        run: |
-          cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
-
-      - name: Upload consolidated report
-        uses: actions/upload-artifact@v4
-        with:
-          name: consolidated_test_report
-          path: ${{ env.CONSOLIDATED_REPORT_PATH }}
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
@@ -633,7 +443,7 @@ jobs:
 #        shell: arch -arch arm64 bash {0}
 #        env:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
 #        run: |
 #          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
@@ -689,7 +499,7 @@ jobs:
 #        shell: arch -arch arm64 bash {0}
 #        env:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
-#          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+#          HF_TOKEN: ${{ secrets.HF_TOKEN }}
 #        run: |
 #          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
@@ -709,4 +519,4 @@ jobs:
 #        if: always()
 #        run: |
 #          pip install slack_sdk tabulate
-#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+#          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/pr_style_bot.yml

@@ -1,17 +0,0 @@
-name: PR Style Bot
-
-on:
-  issue_comment:
-    types: [created]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  style:
-    uses: huggingface/huggingface_hub/.github/workflows/style-bot-action.yml@main
-    with:
-      python_quality_dependencies: "[quality]"
-    secrets:
-      bot_token: ${{ secrets.HF_STYLE_BOT_ACTION }}

.github/workflows/pr_test_peft_backend.yml

@@ -0,0 +1,134 @@
+name: Fast tests for PRs - PEFT backend
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "src/diffusers/**.py"
+      - "tests/**.py"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DIFFUSERS_IS_CI: yes
+  OMP_NUM_THREADS: 4
+  MKL_NUM_THREADS: 4
+  PYTEST_TIMEOUT: 60
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: make quality
+      - name: Check if failure
+        if: ${{ failure() }}
+        run: |
+          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
+
+  check_repository_consistency:
+    needs: check_code_quality
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check repo consistency
+        run: |
+          python utils/check_copies.py
+          python utils/check_dummies.py
+          make deps_table_check_updated
+      - name: Check if failure
+        if: ${{ failure() }}
+        run: |
+          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
+
+  run_fast_tests:
+    needs: [check_code_quality, check_repository_consistency]
+    strategy:
+      fail-fast: false
+      matrix:
+        lib-versions: ["main", "latest"]
+
+
+    name: LoRA - ${{ matrix.lib-versions }}
+
+    runs-on:
+      group: aws-general-8-plus
+
+    container:
+      image: diffusers/diffusers-pytorch-cpu
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        # TODO (sayakpaul, DN6): revisit `--no-deps`
+        if [ "${{ matrix.lib-versions }}" == "main" ]; then
+            python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
+            python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+            pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        else
+            python -m uv pip install -U peft --no-deps
+            python -m uv pip install -U transformers accelerate --no-deps
+        fi
+
+    - name: Environment
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python utils/print_env.py
+
+    - name: Run fast PyTorch LoRA CPU tests with PEFT backend
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -s -v \
+          --make-reports=tests_${{ matrix.lib-versions }} \
+          tests/lora/
+        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+          -s -v \
+          --make-reports=tests_models_lora_${{ matrix.lib-versions }} \
+          tests/models/ -k "lora"
+
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_${{ matrix.lib-versions }}_failures_short.txt
+        cat reports/tests_models_lora_${{ matrix.lib-versions }}_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: pr_${{ matrix.lib-versions }}_test_reports
+        path: reports

.github/workflows/pr_tests.yml

@@ -2,7 +2,8 @@ name: Fast tests for PRs
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
     paths:
       - "src/diffusers/**.py"
       - "benchmarks/**.py"
@@ -11,7 +12,6 @@ on:
       - "tests/**.py"
       - ".github/**.yml"
       - "utils/**.py"
-      - "setup.py"
   push:
     branches:
       - ci-*
@@ -64,7 +64,6 @@ jobs:
         run: |
           python utils/check_copies.py
           python utils/check_dummies.py
-          python utils/check_support_list.py
           make deps_table_check_updated
       - name: Check if failure
         if: ${{ failure() }}
@@ -121,8 +120,7 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        python -m uv pip install accelerate
 
     - name: Environment
       run: |
@@ -236,68 +234,3 @@ jobs:
       with:
         name: pr_${{ matrix.config.report }}_test_reports
         path: reports
-
-  run_lora_tests:
-    needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
-
-    name: LoRA tests with PEFT main
-
-    runs-on:
-      group: aws-general-8-plus
-
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-
-    defaults:
-      run:
-        shell: bash
-
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        # TODO (sayakpaul, DN6): revisit `--no-deps`
-        python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
-        python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        python -m uv pip install -U tokenizers
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-
-    - name: Environment
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python utils/print_env.py
-
-    - name: Run fast PyTorch LoRA tests with PEFT
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
-          --make-reports=tests_peft_main \
-          tests/lora/
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
-          --make-reports=tests_models_lora_peft_main \
-          tests/models/ -k "lora"
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_peft_main_failures_short.txt
-        cat reports/tests_models_lora_peft_main_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: pr_main_test_reports
-        path: reports
-

.github/workflows/pr_tests_gpu.yml

@@ -1,296 +0,0 @@
-name: Fast GPU Tests on PR 
-
-on:
-  pull_request:
-    branches: main
-    paths:
-      - "src/diffusers/models/modeling_utils.py"
-      - "src/diffusers/models/model_loading_utils.py"
-      - "src/diffusers/pipelines/pipeline_utils.py"
-      - "src/diffusers/pipeline_loading_utils.py"
-      - "src/diffusers/loaders/lora_base.py"
-      - "src/diffusers/loaders/lora_pipeline.py"
-      - "src/diffusers/loaders/peft.py"
-      - "tests/pipelines/test_pipelines_common.py"
-      - "tests/models/test_modeling_common.py"
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-env:
-  DIFFUSERS_IS_CI: yes
-  OMP_NUM_THREADS: 8
-  MKL_NUM_THREADS: 8
-  HF_HUB_ENABLE_HF_TRANSFER: 1
-  PYTEST_TIMEOUT: 600
-  PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
-
-jobs:
-  check_code_quality:
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
-
-  check_repository_consistency:
-    needs: check_code_quality
-    runs-on: ubuntu-22.04
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check repo consistency
-        run: |
-          python utils/check_copies.py
-          python utils/check_dummies.py
-          python utils/check_support_list.py
-          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-  
-  setup_torch_cuda_pipeline_matrix:
-    needs: [check_code_quality, check_repository_consistency]
-    name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on:
-      group: aws-general-8-plus
-    container:
-      image: diffusers/diffusers-pytorch-cpu
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  torch_pipelines_cuda_tests:
-    name: Torch Pipelines CUDA Tests
-    needs: setup_torch_cuda_pipeline_matrix
-    strategy:
-      fail-fast: false
-      max-parallel: 8
-      matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: NVIDIA-SMI
-        run: |
-          nvidia-smi
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Extract tests
-        id: extract_tests
-        run: |
-          pattern=$(python utils/extract_tests_from_mixin.py --type pipeline)
-          echo "$pattern" > /tmp/test_pattern.txt
-          echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
-
-      - name: PyTorch CUDA checkpoint tests on Ubuntu
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
-              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx" \
-              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-              tests/pipelines/${{ matrix.module }}
-          else 
-              pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
-              python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx and $pattern" \
-              --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-              tests/pipelines/${{ matrix.module }}
-          fi 
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: pipeline_${{ matrix.module }}_test_reports
-          path: reports
-
-  torch_cuda_tests:
-    name: Torch CUDA Tests
-    needs: [check_code_quality, check_repository_consistency]
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        module: [models, schedulers, lora, others]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-
-    - name: Environment
-      run: |
-        python utils/print_env.py
-
-    - name: Extract tests
-      id: extract_tests
-      run: |
-        pattern=$(python utils/extract_tests_from_mixin.py --type ${{ matrix.module }})
-        echo "$pattern" > /tmp/test_pattern.txt
-        echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
-
-    - name: Run PyTorch CUDA tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
-        if [ -z "$pattern" ]; then
-          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}  
-        else
-          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
-          --make-reports=tests_torch_cuda_${{ matrix.module }}  
-        fi
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
-        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: torch_cuda_test_reports_${{ matrix.module }}
-        path: reports
-
-  run_examples_tests:
-    name: Examples PyTorch CUDA tests on Ubuntu
-    needs: [check_code_quality, check_repository_consistency]
-    runs-on:
-      group: aws-g4dn-2xlarge
-
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: |
-        nvidia-smi
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        python -m uv pip install -e [quality,test,training]
-
-    - name: Environment
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python utils/print_env.py
-
-    - name: Run example tests on GPU
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install timm
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/examples_torch_cuda_stats.txt
-        cat reports/examples_torch_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: examples_test_reports
-        path: reports
-

.github/workflows/push_tests.yml

@@ -83,7 +83,7 @@ jobs:
           python utils/print_env.py
       - name: PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -137,7 +137,7 @@ jobs:
 
     - name: Run PyTorch CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -161,11 +161,10 @@ jobs:
 
   flax_tpu_tests:
     name: Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
+    runs-on: docker-tpu
     container:
       image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache 
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash
@@ -187,7 +186,7 @@ jobs:
 
     - name: Run Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -235,7 +234,7 @@ jobs:
 
     - name: Run ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -262,7 +261,7 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-cuda
+      image: diffusers/diffusers-pytorch-compile-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
@@ -283,7 +282,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
@@ -326,7 +325,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -349,6 +348,7 @@ jobs:
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
+
     steps:
     - name: Checkout diffusers
       uses: actions/checkout@v3
@@ -358,6 +358,7 @@ jobs:
     - name: NVIDIA-SMI
       run: |
         nvidia-smi
+
     - name: Install dependencies
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
@@ -370,7 +371,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/push_tests_mps.yml

@@ -46,7 +46,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       run: |
         ${CONDA_RUN} python -m pip install --upgrade pip uv
-        ${CONDA_RUN} python -m uv pip install -e ".[quality,test]"
+        ${CONDA_RUN} python -m uv pip install -e [quality,test]
         ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
         ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
         ${CONDA_RUN} python -m uv pip install transformers --upgrade

.github/workflows/pypi_publish.yaml

@@ -68,7 +68,7 @@ jobs:
       - name: Test installing diffusers and importing
         run: |
           pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://test.pypi.org/simple/ diffusers
+          pip install -i https://testpypi.python.org/pypi diffusers
           python -c "from diffusers import __version__; print(__version__)"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('fusing/unet-ldm-dummy-update'); pipe()"
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"

.github/workflows/release_tests_fast.yml

@@ -81,7 +81,7 @@ jobs:
           python utils/print_env.py
       - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -135,7 +135,7 @@ jobs:
 
     - name: Run PyTorch CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -157,63 +157,6 @@ jobs:
         name: torch_cuda_${{ matrix.module }}_test_reports
         path: reports
 
-  torch_minimum_version_cuda_tests:
-    name: Torch Minimum Version CUDA Tests
-    runs-on:
-      group: aws-g4dn-2xlarge
-    container:
-      image: diffusers/diffusers-pytorch-minimum-cuda
-      options: --shm-size "16gb" --ipc host --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-
-      - name: Environment
-        run: |
-          python utils/print_env.py
-
-      - name: Run PyTorch CUDA tests
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_torch_minimum_cuda \
-            tests/models/test_modeling_common.py \
-            tests/pipelines/test_pipelines_common.py \
-            tests/pipelines/test_pipeline_utils.py \
-            tests/pipelines/test_pipelines.py \
-            tests/pipelines/test_pipelines_auto.py \
-            tests/schedulers/test_schedulers.py \
-            tests/others
-
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_torch_minimum_version_cuda_stats.txt
-          cat reports/tests_torch_minimum_version_cuda_failures_short.txt
-
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_minimum_version_cuda_test_reports
-          path: reports
-          
   flax_tpu_tests:
     name: Flax TPU Tests
     runs-on: docker-tpu
@@ -241,7 +184,7 @@ jobs:
 
     - name: Run slow Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -289,7 +232,7 @@ jobs:
 
     - name: Run slow ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -316,7 +259,7 @@ jobs:
       group: aws-g4dn-2xlarge
 
     container:
-      image: diffusers/diffusers-pytorch-cuda
+      image: diffusers/diffusers-pytorch-compile-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host
 
     steps:
@@ -335,9 +278,9 @@ jobs:
     - name: Environment
       run: |
         python utils/print_env.py
-    - name: Run torch compile tests on GPU
+    - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
@@ -380,7 +323,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -426,7 +369,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/run_tests_from_a_pr.yml

@@ -7,8 +7,8 @@ on:
         default: 'diffusers/diffusers-pytorch-cuda'
         description: 'Name of the Docker image'
         required: true
-      pr_number:
-        description: 'PR number to test on'
+      branch:
+        description: 'PR Branch to test on'
         required: true
       test:
         description: 'Tests to run (e.g.: `tests/models`).'
@@ -43,8 +43,8 @@ jobs:
             exit 1
           fi
 
-          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines|lora) ]]; then
-            echo "Error: The input string must contain either 'models', 'pipelines', or 'lora' after 'tests/'."
+          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines) ]]; then
+            echo "Error: The input string must contain either 'models' or 'pipelines' after 'tests/'."
             exit 1
           fi
 
@@ -53,13 +53,13 @@ jobs:
             exit 1
           fi
           echo "$PY_TEST"
-        
-        shell: bash -e {0}
 
       - name: Checkout PR branch
         uses: actions/checkout@v4
         with:
-          ref: refs/pull/${{ inputs.pr_number }}/head
+          ref: ${{ github.event.inputs.branch }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+
 
       - name: Install pytest
         run: |

.github/workflows/trufflehog.yml

@@ -13,6 +13,3 @@ jobs:
         fetch-depth: 0
     - name: Secret Scanning
       uses: trufflesecurity/trufflehog@main
-      with:
-        extra_args: --results=verified,unknown
-

README.md

@@ -112,8 +112,8 @@ Check out the [Quickstart](https://huggingface.co/docs/diffusers/quicktour) to l
 | **Documentation**                                                   | **What can I learn?**                                                                                                                                                                           |
 |---------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | [Tutorial](https://huggingface.co/docs/diffusers/tutorials/tutorial_overview)                                                            | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model.  |
-| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
-| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/overview_techniques)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
+| [Loading](https://huggingface.co/docs/diffusers/using-diffusers/loading_overview)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |
+| [Pipelines for inference](https://huggingface.co/docs/diffusers/using-diffusers/pipeline_overview)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |
 | [Optimization](https://huggingface.co/docs/diffusers/optimization/fp16)                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |
 | [Training](https://huggingface.co/docs/diffusers/training/overview) | Guides for how to train a diffusion model for different tasks with different training techniques.                                                                                               |
 ## Contribution

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -28,9 +28,9 @@ ENV PATH="/opt/venv/bin:$PATH"
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
 RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     python3 -m uv pip install --no-cache-dir \
-        torch \
-        torchvision \
-        torchaudio\
+        torch==2.1.2 \
+        torchvision==0.16.2 \
+        torchaudio==2.1.2 \
         onnxruntime \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
     python3 -m uv pip install --no-cache-dir \

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -3,9 +3,6 @@ LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
 ENV DEBIAN_FRONTEND=noninteractive
-ENV MINIMUM_SUPPORTED_TORCH_VERSION="2.1.0"
-ENV MINIMUM_SUPPORTED_TORCHVISION_VERSION="0.16.0"
-ENV MINIMUM_SUPPORTED_TORCHAUDIO_VERSION="2.1.0"
 
 RUN apt-get -y update \
     && apt-get install -y software-properties-common \
@@ -32,9 +29,9 @@ ENV PATH="/opt/venv/bin:$PATH"
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
 RUN python3.10 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
     python3.10 -m uv pip install --no-cache-dir \
-    torch==$MINIMUM_SUPPORTED_TORCH_VERSION \
-    torchvision==$MINIMUM_SUPPORTED_TORCHVISION_VERSION \
-    torchaudio==$MINIMUM_SUPPORTED_TORCHAUDIO_VERSION \
+    torch \
+    torchvision \
+    torchaudio \
     invisible_watermark && \
     python3.10 -m pip install --no-cache-dir \
     accelerate \

docs/source/en/_toctree.yml

@@ -17,6 +17,12 @@
     title: AutoPipeline
   - local: tutorials/basic_training
     title: Train a diffusion model
+  - local: tutorials/using_peft_for_inference
+    title: Load LoRAs for inference
+  - local: tutorials/fast_diffusion
+    title: Accelerate inference of text-to-image diffusion models
+  - local: tutorials/inference_with_big_models
+    title: Working with big models
   title: Tutorials
 - sections:
   - local: using-diffusers/loading
@@ -27,24 +33,11 @@
     title: Load schedulers and models
   - local: using-diffusers/other-formats
     title: Model files and layouts
+  - local: using-diffusers/loading_adapters
+    title: Load adapters
   - local: using-diffusers/push_to_hub
     title: Push files to the Hub
   title: Load pipelines and adapters
-- sections:
-  - local: tutorials/using_peft_for_inference
-    title: LoRA
-  - local: using-diffusers/ip_adapter
-    title: IP-Adapter
-  - local: using-diffusers/controlnet
-    title: ControlNet
-  - local: using-diffusers/t2i_adapter
-    title: T2I-Adapter
-  - local: using-diffusers/dreambooth
-    title: DreamBooth
-  - local: using-diffusers/textual_inversion_inference
-    title: Textual inversion
-  title: Adapters
-  isExpanded: false
 - sections:
   - local: using-diffusers/unconditional_image_generation
     title: Unconditional image generation
@@ -55,7 +48,7 @@
   - local: using-diffusers/inpaint
     title: Inpainting
   - local: using-diffusers/text-img2vid
-    title: Video generation
+    title: Text or image-to-video
   - local: using-diffusers/depth2img
     title: Depth-to-image
   title: Generative tasks
@@ -66,6 +59,8 @@
     title: Create a server
   - local: training/distributed_inference
     title: Distributed inference
+  - local: using-diffusers/merge_loras
+    title: Merge LoRAs
   - local: using-diffusers/scheduler_features
     title: Scheduler features
   - local: using-diffusers/callback
@@ -82,30 +77,26 @@
     title: Outpainting
   title: Advanced inference
 - sections:
-  - local: hybrid_inference/overview
-    title: Overview
-  - local: hybrid_inference/vae_decode
-    title: VAE Decode
-  - local: hybrid_inference/vae_encode
-    title: VAE Encode
-  - local: hybrid_inference/api_reference
-    title: API Reference
-  title: Hybrid Inference
-- sections:
-  - local: using-diffusers/consisid
-    title: ConsisID
+  - local: using-diffusers/cogvideox
+    title: CogVideoX
   - local: using-diffusers/sdxl
     title: Stable Diffusion XL
   - local: using-diffusers/sdxl_turbo
     title: SDXL Turbo
   - local: using-diffusers/kandinsky
     title: Kandinsky
-  - local: using-diffusers/omnigen
-    title: OmniGen
+  - local: using-diffusers/ip_adapter
+    title: IP-Adapter
   - local: using-diffusers/pag
     title: PAG
+  - local: using-diffusers/controlnet
+    title: ControlNet
+  - local: using-diffusers/t2i_adapter
+    title: T2I-Adapter
   - local: using-diffusers/inference_with_lcm
     title: Latent Consistency Model
+  - local: using-diffusers/textual_inversion_inference
+    title: Textual inversion
   - local: using-diffusers/shap-e
     title: Shap-E
   - local: using-diffusers/diffedit
@@ -166,22 +157,14 @@
     title: Getting Started
   - local: quantization/bitsandbytes
     title: bitsandbytes
-  - local: quantization/gguf
-    title: gguf
-  - local: quantization/torchao
-    title: torchao
-  - local: quantization/quanto
-    title: quanto
   title: Quantization Methods
 - sections:
   - local: optimization/fp16
-    title: Accelerate inference
-  - local: optimization/cache
-    title: Caching
+    title: Speed up inference
   - local: optimization/memory
     title: Reduce memory usage
-  - local: optimization/pruna
-    title: Pruna
+  - local: optimization/torch2.0
+    title: PyTorch 2.0
   - local: optimization/xformers
     title: xFormers
   - local: optimization/tome
@@ -192,8 +175,6 @@
     title: TGATE
   - local: optimization/xdit
     title: xDiT
-  - local: optimization/para_attn
-    title: ParaAttention
   - sections:
     - local: using-diffusers/stable_diffusion_jax_how_to
       title: JAX/Flax
@@ -208,7 +189,7 @@
     - local: optimization/mps
       title: Metal Performance Shaders (MPS)
     - local: optimization/habana
-      title: Intel Gaudi
+      title: Habana Gaudi
     - local: optimization/neuron
       title: AWS Neuron
     title: Optimized hardware
@@ -253,8 +234,6 @@
       title: Textual Inversion
     - local: api/loaders/unet
       title: UNet
-    - local: api/loaders/transformer_sd3
-      title: SD3Transformer2D
     - local: api/loaders/peft
       title: PEFT
     title: Loaders
@@ -262,19 +241,13 @@
     sections:
     - local: api/models/overview
       title: Overview
-    - local: api/models/auto_model
-      title: AutoModel
     - sections:
       - local: api/models/controlnet
         title: ControlNetModel
-      - local: api/models/controlnet_union
-        title: ControlNetUnionModel
       - local: api/models/controlnet_flux
         title: FluxControlNetModel
       - local: api/models/controlnet_hunyuandit
         title: HunyuanDiT2DControlNetModel
-      - local: api/models/controlnet_sana
-        title: SanaControlNetModel
       - local: api/models/controlnet_sd3
         title: SD3ControlNetModel
       - local: api/models/controlnet_sparsectrl
@@ -285,48 +258,26 @@
         title: AllegroTransformer3DModel
       - local: api/models/aura_flow_transformer2d
         title: AuraFlowTransformer2DModel
-      - local: api/models/chroma_transformer
-        title: ChromaTransformer2DModel
       - local: api/models/cogvideox_transformer3d
         title: CogVideoXTransformer3DModel
       - local: api/models/cogview3plus_transformer2d
         title: CogView3PlusTransformer2DModel
-      - local: api/models/cogview4_transformer2d
-        title: CogView4Transformer2DModel
-      - local: api/models/consisid_transformer3d
-        title: ConsisIDTransformer3DModel
-      - local: api/models/cosmos_transformer3d
-        title: CosmosTransformer3DModel
       - local: api/models/dit_transformer2d
         title: DiTTransformer2DModel
-      - local: api/models/easyanimate_transformer3d
-        title: EasyAnimateTransformer3DModel
       - local: api/models/flux_transformer
         title: FluxTransformer2DModel
-      - local: api/models/hidream_image_transformer
-        title: HiDreamImageTransformer2DModel
       - local: api/models/hunyuan_transformer2d
         title: HunyuanDiT2DModel
-      - local: api/models/hunyuan_video_transformer_3d
-        title: HunyuanVideoTransformer3DModel
       - local: api/models/latte_transformer3d
         title: LatteTransformer3DModel
-      - local: api/models/ltx_video_transformer3d
-        title: LTXVideoTransformer3DModel
-      - local: api/models/lumina2_transformer2d
-        title: Lumina2Transformer2DModel
       - local: api/models/lumina_nextdit2d
         title: LuminaNextDiT2DModel
       - local: api/models/mochi_transformer3d
         title: MochiTransformer3DModel
-      - local: api/models/omnigen_transformer
-        title: OmniGenTransformer2DModel
       - local: api/models/pixart_transformer2d
         title: PixArtTransformer2DModel
       - local: api/models/prior_transformer
         title: PriorTransformer
-      - local: api/models/sana_transformer2d
-        title: SanaTransformer2DModel
       - local: api/models/sd3_transformer2d
         title: SD3Transformer2DModel
       - local: api/models/stable_audio_transformer
@@ -335,18 +286,16 @@
         title: Transformer2DModel
       - local: api/models/transformer_temporal
         title: TransformerTemporalModel
-      - local: api/models/wan_transformer_3d
-        title: WanTransformer3DModel
       title: Transformers
     - sections:
       - local: api/models/stable_cascade_unet
         title: StableCascadeUNet
       - local: api/models/unet
         title: UNet1DModel
-      - local: api/models/unet2d-cond
-        title: UNet2DConditionModel
       - local: api/models/unet2d
         title: UNet2DModel
+      - local: api/models/unet2d-cond
+        title: UNet2DConditionModel
       - local: api/models/unet3d-cond
         title: UNet3DConditionModel
       - local: api/models/unet-motion
@@ -355,28 +304,16 @@
         title: UViT2DModel
       title: UNets
     - sections:
-      - local: api/models/asymmetricautoencoderkl
-        title: AsymmetricAutoencoderKL
-      - local: api/models/autoencoder_dc
-        title: AutoencoderDC
       - local: api/models/autoencoderkl
         title: AutoencoderKL
       - local: api/models/autoencoderkl_allegro
         title: AutoencoderKLAllegro
       - local: api/models/autoencoderkl_cogvideox
         title: AutoencoderKLCogVideoX
-      - local: api/models/autoencoderkl_cosmos
-        title: AutoencoderKLCosmos
-      - local: api/models/autoencoder_kl_hunyuan_video
-        title: AutoencoderKLHunyuanVideo
-      - local: api/models/autoencoderkl_ltx_video
-        title: AutoencoderKLLTXVideo
-      - local: api/models/autoencoderkl_magvit
-        title: AutoencoderKLMagvit
       - local: api/models/autoencoderkl_mochi
         title: AutoencoderKLMochi
-      - local: api/models/autoencoder_kl_wan
-        title: AutoencoderKLWan
+      - local: api/models/asymmetricautoencoderkl
+        title: AsymmetricAutoencoderKL
       - local: api/models/consistency_decoder_vae
         title: ConsistencyDecoderVAE
       - local: api/models/autoencoder_oobleck
@@ -409,16 +346,10 @@
       title: AutoPipeline
     - local: api/pipelines/blip_diffusion
       title: BLIP-Diffusion
-    - local: api/pipelines/chroma
-      title: Chroma
     - local: api/pipelines/cogvideox
       title: CogVideoX
     - local: api/pipelines/cogview3
       title: CogView3
-    - local: api/pipelines/cogview4
-      title: CogView4
-    - local: api/pipelines/consisid
-      title: ConsisID
     - local: api/pipelines/consistency_models
       title: Consistency Models
     - local: api/pipelines/controlnet
@@ -431,16 +362,10 @@
       title: ControlNet with Stable Diffusion 3
     - local: api/pipelines/controlnet_sdxl
       title: ControlNet with Stable Diffusion XL
-    - local: api/pipelines/controlnet_sana
-      title: ControlNet-Sana
     - local: api/pipelines/controlnetxs
       title: ControlNet-XS
     - local: api/pipelines/controlnetxs_sdxl
       title: ControlNet-XS with Stable Diffusion XL
-    - local: api/pipelines/controlnet_union
-      title: ControlNetUnion
-    - local: api/pipelines/cosmos
-      title: Cosmos
     - local: api/pipelines/dance_diffusion
       title: Dance Diffusion
     - local: api/pipelines/ddim
@@ -453,20 +378,10 @@
       title: DiffEdit
     - local: api/pipelines/dit
       title: DiT
-    - local: api/pipelines/easyanimate
-      title: EasyAnimate
     - local: api/pipelines/flux
       title: Flux
-    - local: api/pipelines/control_flux_inpaint
-      title: FluxControlInpaint
-    - local: api/pipelines/framepack
-      title: Framepack
-    - local: api/pipelines/hidream
-      title: HiDream-I1
     - local: api/pipelines/hunyuandit
       title: Hunyuan-DiT
-    - local: api/pipelines/hunyuan_video
-      title: HunyuanVideo
     - local: api/pipelines/i2vgenxl
       title: I2VGen-XL
     - local: api/pipelines/pix2pix
@@ -487,10 +402,6 @@
       title: Latte
     - local: api/pipelines/ledits_pp
       title: LEDITS++
-    - local: api/pipelines/ltx_video
-      title: LTXVideo
-    - local: api/pipelines/lumina2
-      title: Lumina 2.0
     - local: api/pipelines/lumina
       title: Lumina-T2X
     - local: api/pipelines/marigold
@@ -501,8 +412,6 @@
       title: MultiDiffusion
     - local: api/pipelines/musicldm
       title: MusicLDM
-    - local: api/pipelines/omnigen
-      title: OmniGen
     - local: api/pipelines/pag
       title: PAG
     - local: api/pipelines/paint_by_example
@@ -513,10 +422,6 @@
       title: PixArt-α
     - local: api/pipelines/pixart_sigma
       title: PixArt-Σ
-    - local: api/pipelines/sana
-      title: Sana
-    - local: api/pipelines/sana_sprint
-      title: Sana Sprint
     - local: api/pipelines/self_attention_guidance
       title: Self-Attention Guidance
     - local: api/pipelines/semantic_stable_diffusion
@@ -530,40 +435,40 @@
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
-      - local: api/pipelines/stable_diffusion/depth2img
-        title: Depth-to-image
-      - local: api/pipelines/stable_diffusion/gligen
-        title: GLIGEN (Grounded Language-to-Image Generation)
-      - local: api/pipelines/stable_diffusion/image_variation
-        title: Image variation
+      - local: api/pipelines/stable_diffusion/text2img
+        title: Text-to-image
       - local: api/pipelines/stable_diffusion/img2img
         title: Image-to-image
       - local: api/pipelines/stable_diffusion/svd
         title: Image-to-video
       - local: api/pipelines/stable_diffusion/inpaint
         title: Inpainting
-      - local: api/pipelines/stable_diffusion/k_diffusion
-        title: K-Diffusion
-      - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Latent upscaler
-      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
-        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
+      - local: api/pipelines/stable_diffusion/depth2img
+        title: Depth-to-image
+      - local: api/pipelines/stable_diffusion/image_variation
+        title: Image variation
       - local: api/pipelines/stable_diffusion/stable_diffusion_safe
         title: Safe Stable Diffusion
-      - local: api/pipelines/stable_diffusion/sdxl_turbo
-        title: SDXL Turbo
       - local: api/pipelines/stable_diffusion/stable_diffusion_2
         title: Stable Diffusion 2
       - local: api/pipelines/stable_diffusion/stable_diffusion_3
         title: Stable Diffusion 3
       - local: api/pipelines/stable_diffusion/stable_diffusion_xl
         title: Stable Diffusion XL
+      - local: api/pipelines/stable_diffusion/sdxl_turbo
+        title: SDXL Turbo
+      - local: api/pipelines/stable_diffusion/latent_upscale
+        title: Latent upscaler
       - local: api/pipelines/stable_diffusion/upscale
         title: Super-resolution
+      - local: api/pipelines/stable_diffusion/k_diffusion
+        title: K-Diffusion
+      - local: api/pipelines/stable_diffusion/ldm3d_diffusion
+        title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/adapter
         title: T2I-Adapter
-      - local: api/pipelines/stable_diffusion/text2img
-        title: Text-to-image
+      - local: api/pipelines/stable_diffusion/gligen
+        title: GLIGEN (Grounded Language-to-Image Generation)
       title: Stable Diffusion
     - local: api/pipelines/stable_unclip
       title: Stable unCLIP
@@ -577,10 +482,6 @@
       title: UniDiffuser
     - local: api/pipelines/value_guided_sampling
       title: Value-guided sampling
-    - local: api/pipelines/visualcloze
-      title: VisualCloze
-    - local: api/pipelines/wan
-      title: Wan
     - local: api/pipelines/wuerstchen
       title: Wuerstchen
     title: Pipelines
@@ -590,10 +491,6 @@
       title: Overview
     - local: api/schedulers/cm_stochastic_iterative
       title: CMStochasticIterativeScheduler
-    - local: api/schedulers/ddim_cogvideox
-      title: CogVideoXDDIMScheduler
-    - local: api/schedulers/multistep_dpm_solver_cogvideox
-      title: CogVideoXDPMScheduler
     - local: api/schedulers/consistency_decoder
       title: ConsistencyDecoderScheduler
     - local: api/schedulers/cosine_dpm
@@ -663,8 +560,6 @@
       title: Attention Processor
     - local: api/activations
       title: Custom activation functions
-    - local: api/cache
-      title: Caching methods
     - local: api/normalization
       title: Custom normalization layers
     - local: api/utilities

docs/source/en/api/activations.md

@@ -25,16 +25,3 @@ Customized activation functions for supporting various models in 🤗 Diffusers.
 ## ApproximateGELU
 
 [[autodoc]] models.activations.ApproximateGELU
-
-
-## SwiGLU
-
-[[autodoc]] models.activations.SwiGLU
-
-## FP32SiLU
-
-[[autodoc]] models.activations.FP32SiLU
-
-## LinearActivation
-
-[[autodoc]] models.activations.LinearActivation

docs/source/en/api/attnprocessor.md

@@ -15,152 +15,40 @@ specific language governing permissions and limitations under the License.
 An attention processor is a class for applying different types of attention mechanisms.
 
 ## AttnProcessor
-
 [[autodoc]] models.attention_processor.AttnProcessor
 
+## AttnProcessor2_0
 [[autodoc]] models.attention_processor.AttnProcessor2_0
 
+## AttnAddedKVProcessor
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor
 
+## AttnAddedKVProcessor2_0
 [[autodoc]] models.attention_processor.AttnAddedKVProcessor2_0
 
-[[autodoc]] models.attention_processor.AttnProcessorNPU
-
-[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
-
-## Allegro
-
-[[autodoc]] models.attention_processor.AllegroAttnProcessor2_0
-
-## AuraFlow
-
-[[autodoc]] models.attention_processor.AuraFlowAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedAuraFlowAttnProcessor2_0
-
-## CogVideoX
-
-[[autodoc]] models.attention_processor.CogVideoXAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedCogVideoXAttnProcessor2_0
-
 ## CrossFrameAttnProcessor
-
 [[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
 
-## Custom Diffusion
-
+## CustomDiffusionAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor
 
+## CustomDiffusionAttnProcessor2_0
 [[autodoc]] models.attention_processor.CustomDiffusionAttnProcessor2_0
 
+## CustomDiffusionXFormersAttnProcessor
 [[autodoc]] models.attention_processor.CustomDiffusionXFormersAttnProcessor
 
-## Flux
-
-[[autodoc]] models.attention_processor.FluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedFluxAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FluxSingleAttnProcessor2_0
-
-## Hunyuan
-
-[[autodoc]] models.attention_processor.HunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGHunyuanAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGHunyuanAttnProcessor2_0
-
-## IdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySelfAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0
-
-## IP-Adapter
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor
-
-[[autodoc]] models.attention_processor.IPAdapterAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SD3IPAdapterJointAttnProcessor2_0
-
-## JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.JointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FusedJointAttnProcessor2_0
-
-## LoRA
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor
-
-[[autodoc]] models.attention_processor.LoRAAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
-
-[[autodoc]] models.attention_processor.LoRAXFormersAttnProcessor
-
-## Lumina-T2X
-
-[[autodoc]] models.attention_processor.LuminaAttnProcessor2_0
-
-## Mochi
-
-[[autodoc]] models.attention_processor.MochiAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.MochiVaeAttnProcessor2_0
-
-## Sana
-
-[[autodoc]] models.attention_processor.SanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.SanaMultiscaleAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0
-
-## Stable Audio
-
-[[autodoc]] models.attention_processor.StableAudioAttnProcessor2_0
+## FusedAttnProcessor2_0
+[[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
 ## SlicedAttnProcessor
-
 [[autodoc]] models.attention_processor.SlicedAttnProcessor
 
+## SlicedAttnAddedKVProcessor
 [[autodoc]] models.attention_processor.SlicedAttnAddedKVProcessor
 
 ## XFormersAttnProcessor
-
 [[autodoc]] models.attention_processor.XFormersAttnProcessor
 
-[[autodoc]] models.attention_processor.XFormersAttnAddedKVProcessor
-
-## XLAFlashAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.XLAFlashAttnProcessor2_0
-
-## XFormersJointAttnProcessor
-
-[[autodoc]] models.attention_processor.XFormersJointAttnProcessor
-
-## IPAdapterXFormersAttnProcessor
-
-[[autodoc]] models.attention_processor.IPAdapterXFormersAttnProcessor
-
-## FluxIPAdapterJointAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.FluxIPAdapterJointAttnProcessor2_0
-
-
-## XLAFluxFlashAttnProcessor2_0
-
-[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0
+## AttnProcessorNPU
+[[autodoc]] models.attention_processor.AttnProcessorNPU

docs/source/en/api/cache.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# Caching methods
-
-Cache methods speedup diffusion transformers by storing and reusing intermediate outputs of specific layers, such as attention and feedforward layers, instead of recalculating them at each inference step.
-
-## CacheMixin
-
-[[autodoc]] CacheMixin
-
-## PyramidAttentionBroadcastConfig
-
-[[autodoc]] PyramidAttentionBroadcastConfig
-
-[[autodoc]] apply_pyramid_attention_broadcast
-
-## FasterCacheConfig
-
-[[autodoc]] FasterCacheConfig
-
-[[autodoc]] apply_faster_cache

docs/source/en/api/loaders/ip_adapter.md

@@ -24,12 +24,6 @@ Learn how to load an IP-Adapter checkpoint and image in the IP-Adapter [loading]
 
 [[autodoc]] loaders.ip_adapter.IPAdapterMixin
 
-## SD3IPAdapterMixin
-
-[[autodoc]] loaders.ip_adapter.SD3IPAdapterMixin
-    - all
-    - is_ip_adapter_active
-
 ## IPAdapterMaskProcessor
 
 [[autodoc]] image_processor.IPAdapterMaskProcessor

docs/source/en/api/loaders/lora.md

@@ -17,18 +17,7 @@ LoRA is a fast and lightweight training method that inserts and trains a signifi
 - [`StableDiffusionLoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
 - [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`StableDiffusionLoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
 - [`SD3LoraLoaderMixin`] provides similar functions for [Stable Diffusion 3](https://huggingface.co/blog/sd3).
-- [`FluxLoraLoaderMixin`] provides similar functions for [Flux](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux).
-- [`CogVideoXLoraLoaderMixin`] provides similar functions for [CogVideoX](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox).
-- [`Mochi1LoraLoaderMixin`] provides similar functions for [Mochi](https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi).
-- [`AuraFlowLoraLoaderMixin`] provides similar functions for [AuraFlow](https://huggingface.co/fal/AuraFlow).
-- [`LTXVideoLoraLoaderMixin`] provides similar functions for [LTX-Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).
-- [`SanaLoraLoaderMixin`] provides similar functions for [Sana](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana).
-- [`HunyuanVideoLoraLoaderMixin`] provides similar functions for [HunyuanVideo](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video).
-- [`Lumina2LoraLoaderMixin`] provides similar functions for [Lumina2](https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2).
-- [`WanLoraLoaderMixin`] provides similar functions for [Wan](https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan).
-- [`CogView4LoraLoaderMixin`] provides similar functions for [CogView4](https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4).
 - [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
-- [`HiDreamImageLoraLoaderMixin`] provides similar functions for [HiDream Image](https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream)
 - [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
 
 <Tip>
@@ -49,57 +38,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 [[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
 
-## FluxLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.FluxLoraLoaderMixin
-
-## CogVideoXLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.CogVideoXLoraLoaderMixin
-
-## Mochi1LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Mochi1LoraLoaderMixin
-## AuraFlowLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.AuraFlowLoraLoaderMixin
-
-## LTXVideoLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.LTXVideoLoraLoaderMixin
-
-## SanaLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SanaLoraLoaderMixin
-
-## HunyuanVideoLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.HunyuanVideoLoraLoaderMixin
-
-## Lumina2LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.Lumina2LoraLoaderMixin
-
-## CogView4LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.CogView4LoraLoaderMixin
-
-## WanLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin
-
 ## AmusedLoraLoaderMixin
 
 [[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
 
-## HiDreamImageLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.HiDreamImageLoraLoaderMixin
-
 ## LoraBaseMixin
 
-[[autodoc]] loaders.lora_base.LoraBaseMixin
-
-## WanLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin
+[[autodoc]] loaders.lora_base.LoraBaseMixin

docs/source/en/api/loaders/transformer_sd3.md

@@ -1,29 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# SD3Transformer2D
-
-This class is useful when *only* loading weights into a [`SD3Transformer2DModel`]. If you need to load weights into the text encoder or a text encoder and SD3Transformer2DModel, check [`SD3LoraLoaderMixin`](lora#diffusers.loaders.SD3LoraLoaderMixin) class instead.
-
-The [`SD3Transformer2DLoadersMixin`] class currently only loads IP-Adapter weights, but will be used in the future to save weights and load LoRAs.
-
-<Tip>
-
-To learn more about how to load LoRA weights, see the [LoRA](../../using-diffusers/loading_adapters#lora) loading guide.
-
-</Tip>
-
-## SD3Transformer2DLoadersMixin
-
-[[autodoc]] loaders.transformer_sd3.SD3Transformer2DLoadersMixin
-    - all
-    - _load_ip_adapter_weights

docs/source/en/api/models/allegro_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AllegroTransformer3DModel
 
-transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## AllegroTransformer3DModel

docs/source/en/api/models/asymmetricautoencoderkl.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AsymmetricAutoencoderKL
 
-Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://huggingface.co/papers/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
+Improved larger variational autoencoder (VAE) model with KL loss for inpainting task: [Designing a Better Asymmetric VQGAN for StableDiffusion](https://arxiv.org/abs/2306.04632) by Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua.
 
 The abstract from the paper is:
 

docs/source/en/api/models/auto_model.md

@@ -1,29 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# AutoModel
-
-The `AutoModel` is designed to make it easy to load a checkpoint without needing to know the specific model class. `AutoModel` automatically retrieves the correct model class from the checkpoint `config.json` file.
-
-```python
-from diffusers import AutoModel, AutoPipelineForText2Image
-
-unet = AutoModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
-pipe = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet)
-```
-
-
-## AutoModel
-
-[[autodoc]] AutoModel
-	- all
-	- from_pretrained

docs/source/en/api/models/autoencoder_dc.md

@@ -1,72 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderDC
-
-The 2D Autoencoder model used in [SANA](https://huggingface.co/papers/2410.10629) and introduced in [DCAE](https://huggingface.co/papers/2410.10733) by authors Junyu Chen\*, Han Cai\*, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao Lu, Song Han from MIT HAN Lab.
-
-The abstract from the paper is:
-
-*We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at [this https URL](https://github.com/mit-han-lab/efficientvit).*
-
-The following DCAE models are released and supported in Diffusers.
-
-| Diffusers format | Original format |
-|:----------------:|:---------------:|
-| [`mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-sana-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0)
-| [`mit-han-lab/dc-ae-f32c32-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-in-1.0)
-| [`mit-han-lab/dc-ae-f32c32-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f32c32-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f32c32-mix-1.0)
-| [`mit-han-lab/dc-ae-f64c128-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f64c128-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0)
-| [`mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f64c128-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f64c128-mix-1.0)
-| [`mit-han-lab/dc-ae-f128c512-in-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-in-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0)
-| [`mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0-diffusers) | [`mit-han-lab/dc-ae-f128c512-mix-1.0`](https://huggingface.co/mit-han-lab/dc-ae-f128c512-mix-1.0)
-
-This model was contributed by [lawrence-cj](https://github.com/lawrence-cj).
-
-Load a model in Diffusers format with [`~ModelMixin.from_pretrained`].
-
-```python
-from diffusers import AutoencoderDC
-
-ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers", torch_dtype=torch.float32).to("cuda")
-```
-
-## Load a model in Diffusers via `from_single_file`
-
-```python
-from difusers import AutoencoderDC
-
-ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.0/blob/main/model.safetensors"
-model = AutoencoderDC.from_single_file(ckpt_path) 
-
-```
-
-The `AutoencoderDC` model has `in` and `mix` single file checkpoint variants that have matching checkpoint keys, but use different scaling factors. It is not possible for Diffusers to automatically infer the correct config file to use with the model based on just the checkpoint and will default to configuring the model using the `mix` variant config file. To override the automatically determined config, please use the `config` argument when using single file loading with `in` variant checkpoints. 
-
-```python
-from diffusers import AutoencoderDC
-
-ckpt_path = "https://huggingface.co/mit-han-lab/dc-ae-f128c512-in-1.0/blob/main/model.safetensors"
-model = AutoencoderDC.from_single_file(ckpt_path, config="mit-han-lab/dc-ae-f128c512-in-1.0-diffusers")
-```
-
-
-## AutoencoderDC
-
-[[autodoc]] AutoencoderDC
-  - encode
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput
-

docs/source/en/api/models/autoencoder_kl_hunyuan_video.md

@@ -1,32 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLHunyuanVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [HunyuanVideo](https://github.com/Tencent/HunyuanVideo/), which was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLHunyuanVideo
-
-vae = AutoencoderKLHunyuanVideo.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="vae", torch_dtype=torch.float16)
-```
-
-## AutoencoderKLHunyuanVideo
-
-[[autodoc]] AutoencoderKLHunyuanVideo
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoder_kl_wan.md

@@ -1,32 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLWan
-
-The 3D variational autoencoder (VAE) model with KL loss used in [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLWan
-
-vae = AutoencoderKLWan.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="vae", torch_dtype=torch.float32)
-```
-
-## AutoencoderKLWan
-
-[[autodoc]] AutoencoderKLWan
-  - decode
-  - all
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoderkl.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AutoencoderKL
 
-The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://huggingface.co/papers/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
+The variational autoencoder (VAE) model with KL loss was introduced in [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114v11) by Diederik P. Kingma and Max Welling. The model is used in 🤗 Diffusers to encode images into latents and to decode latent representations into images.
 
 The abstract from the paper is:
 

docs/source/en/api/models/autoencoderkl_allegro.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLAllegro
 
-vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32).to("cuda")
+vae = AutoencoderKLCogVideoX.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32).to("cuda")
 ```
 
 ## AutoencoderKLAllegro

docs/source/en/api/models/autoencoderkl_cosmos.md

@@ -1,40 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLCosmos
-
-[Cosmos Tokenizers](https://github.com/NVIDIA/Cosmos-Tokenizer).
-
-Supported models:
-- [nvidia/Cosmos-1.0-Tokenizer-CV8x8x8](https://huggingface.co/nvidia/Cosmos-1.0-Tokenizer-CV8x8x8)
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLCosmos
-
-vae = AutoencoderKLCosmos.from_pretrained("nvidia/Cosmos-1.0-Tokenizer-CV8x8x8", subfolder="vae")
-```
-
-## AutoencoderKLCosmos
-
-[[autodoc]] AutoencoderKLCosmos
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoderkl_ltx_video.md

@@ -1,37 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLLTXVideo
-
-The 3D variational autoencoder (VAE) model with KL loss used in [LTX](https://huggingface.co/Lightricks/LTX-Video) was introduced by Lightricks.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLLTXVideo
-
-vae = AutoencoderKLLTXVideo.from_pretrained("Lightricks/LTX-Video", subfolder="vae", torch_dtype=torch.float32).to("cuda")
-```
-
-## AutoencoderKLLTXVideo
-
-[[autodoc]] AutoencoderKLLTXVideo
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/autoencoderkl_magvit.md

@@ -1,37 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# AutoencoderKLMagvit
-
-The 3D variational autoencoder (VAE) model with KL loss used in [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import AutoencoderKLMagvit
-
-vae = AutoencoderKLMagvit.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="vae", torch_dtype=torch.float16).to("cuda")
-```
-
-## AutoencoderKLMagvit
-
-[[autodoc]] AutoencoderKLMagvit
-    - decode
-    - encode
-    - all
-
-## AutoencoderKLOutput
-
-[[autodoc]] models.autoencoders.autoencoder_kl.AutoencoderKLOutput
-
-## DecoderOutput
-
-[[autodoc]] models.autoencoders.vae.DecoderOutput

docs/source/en/api/models/chroma_transformer.md

@@ -1,19 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# ChromaTransformer2DModel
-
-A modified flux Transformer model from [Chroma](https://huggingface.co/lodestones/Chroma)
-
-## ChromaTransformer2DModel
-
-[[autodoc]] ChromaTransformer2DModel

docs/source/en/api/models/cogvideox_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogVideoXTransformer3DModel
 
-transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## CogVideoXTransformer3DModel

docs/source/en/api/models/cogview3plus_transformer2d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogView3PlusTransformer2DModel
 
-transformer = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
+vae = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
 ```
 
 ## CogView3PlusTransformer2DModel

docs/source/en/api/models/cogview4_transformer2d.md

@@ -1,30 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# CogView4Transformer2DModel
-
-A Diffusion Transformer model for 2D data from [CogView4]()
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import CogView4Transformer2DModel
-
-transformer = CogView4Transformer2DModel.from_pretrained("THUDM/CogView4-6B", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
-```
-
-## CogView4Transformer2DModel
-
-[[autodoc]] CogView4Transformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/consisid_transformer3d.md

@@ -1,30 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# ConsisIDTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [ConsisID](https://github.com/PKU-YuanGroup/ConsisID) was introduced in [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) by Peking University & University of Rochester & etc.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import ConsisIDTransformer3DModel
-
-transformer = ConsisIDTransformer3DModel.from_pretrained("BestWishYsh/ConsisID-preview", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
-```
-
-## ConsisIDTransformer3DModel
-
-[[autodoc]] ConsisIDTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/controlnet_hunyuandit.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # HunyuanDiT2DControlNetModel
 
-HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://huggingface.co/papers/2405.08748).
+HunyuanDiT2DControlNetModel is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 

docs/source/en/api/models/controlnet_sana.md

@@ -1,29 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# SanaControlNetModel
-
-The ControlNet model was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, Maneesh Agrawala. It provides a greater degree of control over text-to-image generation by conditioning the model on additional inputs such as edge maps, depth maps, segmentation maps, and keypoints for pose detection.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This model was contributed by [ishan24](https://huggingface.co/ishan24). ❤️
-The original codebase can be found at [NVlabs/Sana](https://github.com/NVlabs/Sana), and you can find official ControlNet checkpoints on [Efficient-Large-Model's](https://huggingface.co/Efficient-Large-Model) Hub profile.
-
-## SanaControlNetModel
-[[autodoc]] SanaControlNetModel
-
-## SanaControlNetOutput
-[[autodoc]] models.controlnets.controlnet_sana.SanaControlNetOutput
-

docs/source/en/api/models/controlnet_sparsectrl.md

@@ -11,11 +11,11 @@ specific language governing permissions and limitations under the License. -->
 
 # SparseControlNetModel
 
-SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://huggingface.co/papers/2307.04725).
+SparseControlNetModel is an implementation of ControlNet for [AnimateDiff](https://arxiv.org/abs/2307.04725).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
-The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+The SparseCtrl version of ControlNet was introduced in [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
 
 The abstract from the paper is:
 

docs/source/en/api/models/controlnet_union.md

@@ -1,35 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team and The InstantX Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# ControlNetUnionModel
-
-ControlNetUnionModel is an implementation of ControlNet for Stable Diffusion XL.
-
-The ControlNet model was introduced in [ControlNetPlus](https://github.com/xinsir6/ControlNetPlus) by xinsir6. It supports multiple conditioning inputs without increasing computation.
-
-*We design a new architecture that can support 10+ control types in condition text-to-image generation and can generate high resolution images visually comparable with midjourney. The network is based on the original ControlNet architecture, we propose two new modules to: 1 Extend the original ControlNet to support different image conditions using the same network parameter. 2 Support multiple conditions input without increasing computation offload, which is especially important for designers who want to edit image in detail, different conditions use the same condition encoder, without adding extra computations or parameters.*
-
-## Loading
-
-By default the [`ControlNetUnionModel`] should be loaded with [`~ModelMixin.from_pretrained`].
-
-```py
-from diffusers import StableDiffusionXLControlNetUnionPipeline, ControlNetUnionModel
-
-controlnet = ControlNetUnionModel.from_pretrained("xinsir/controlnet-union-sdxl-1.0")
-pipe = StableDiffusionXLControlNetUnionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet)
-```
-
-## ControlNetUnionModel
-
-[[autodoc]] ControlNetUnionModel
-

docs/source/en/api/models/cosmos_transformer3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# CosmosTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import CosmosTransformer3DModel
-
-transformer = CosmosTransformer3DModel.from_pretrained("nvidia/Cosmos-1.0-Diffusion-7B-Text2World", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## CosmosTransformer3DModel
-
-[[autodoc]] CosmosTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/easyanimate_transformer3d.md

@@ -1,30 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# EasyAnimateTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [EasyAnimate](https://github.com/aigc-apps/EasyAnimate) was introduced by Alibaba PAI.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import EasyAnimateTransformer3DModel
-
-transformer = EasyAnimateTransformer3DModel.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
-```
-
-## EasyAnimateTransformer3DModel
-
-[[autodoc]] EasyAnimateTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/hidream_image_transformer.md

@@ -1,46 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# HiDreamImageTransformer2DModel
-
-A Transformer model for image-like data from [HiDream-I1](https://huggingface.co/HiDream-ai).
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HiDreamImageTransformer2DModel
-
-transformer = HiDreamImageTransformer2DModel.from_pretrained("HiDream-ai/HiDream-I1-Full", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## Loading GGUF quantized checkpoints for HiDream-I1
-
-GGUF checkpoints for the `HiDreamImageTransformer2DModel` can  be loaded using `~FromOriginalModelMixin.from_single_file`
-
-```python
-import torch
-from diffusers import GGUFQuantizationConfig, HiDreamImageTransformer2DModel
-
-ckpt_path = "https://huggingface.co/city96/HiDream-I1-Dev-gguf/blob/main/hidream-i1-dev-Q2_K.gguf"
-transformer = HiDreamImageTransformer2DModel.from_single_file(
-    ckpt_path,
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16
-)
-```
-
-## HiDreamImageTransformer2DModel
-
-[[autodoc]] HiDreamImageTransformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/hunyuan_video_transformer_3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# HunyuanVideoTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://huggingface.co/papers/2412.03603) by Tencent.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import HunyuanVideoTransformer3DModel
-
-transformer = HunyuanVideoTransformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## HunyuanVideoTransformer3DModel
-
-[[autodoc]] HunyuanVideoTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/ltx_video_transformer3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# LTXVideoTransformer3DModel
-
-A Diffusion Transformer model for 3D data from [LTX](https://huggingface.co/Lightricks/LTX-Video) was introduced by Lightricks.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import LTXVideoTransformer3DModel
-
-transformer = LTXVideoTransformer3DModel.from_pretrained("Lightricks/LTX-Video", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")
-```
-
-## LTXVideoTransformer3DModel
-
-[[autodoc]] LTXVideoTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/lumina2_transformer2d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# Lumina2Transformer2DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [Lumina Image 2.0](https://huggingface.co/Alpha-VLLM/Lumina-Image-2.0) by Alpha-VLLM.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import Lumina2Transformer2DModel
-
-transformer = Lumina2Transformer2DModel.from_pretrained("Alpha-VLLM/Lumina-Image-2.0", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## Lumina2Transformer2DModel
-
-[[autodoc]] Lumina2Transformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/mochi_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import MochiTransformer3DModel
 
-transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
+vae = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")
 ```
 
 ## MochiTransformer3DModel

docs/source/en/api/models/omnigen_transformer.md

@@ -1,30 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# OmniGenTransformer2DModel
-
-A Transformer model that accepts multimodal instructions to generate images for [OmniGen](https://github.com/VectorSpaceLab/OmniGen/).
-
-The abstract from the paper is:
-
-*The emergence of Large Language Models (LLMs) has unified language  generation tasks and revolutionized human-machine interaction.  However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model’s reasoning capabilities and potential applications of the chain-of-thought mechanism.  This work represents the first attempt at a general-purpose image generation model,  and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.*
-
-```python
-import torch
-from diffusers import OmniGenTransformer2DModel
-
-transformer = OmniGenTransformer2DModel.from_pretrained("Shitao/OmniGen-v1-diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## OmniGenTransformer2DModel
-
-[[autodoc]] OmniGenTransformer2DModel

docs/source/en/api/models/sana_transformer2d.md

@@ -1,34 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# SanaTransformer2DModel
-
-A Diffusion Transformer model for 2D data from [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://huggingface.co/papers/2410.10629) was introduced from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.
-
-The abstract from the paper is:
-
-*We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. Code and model will be publicly released.*
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import SanaTransformer2DModel
-
-transformer = SanaTransformer2DModel.from_pretrained("Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## SanaTransformer2DModel
-
-[[autodoc]] SanaTransformer2DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/models/wan_transformer_3d.md

@@ -1,30 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License. -->
-
-# WanTransformer3DModel
-
-A Diffusion Transformer model for 3D video-like data was introduced in [Wan 2.1](https://github.com/Wan-Video/Wan2.1) by the Alibaba Wan Team.
-
-The model can be loaded with the following code snippet.
-
-```python
-from diffusers import WanTransformer3DModel
-
-transformer = WanTransformer3DModel.from_pretrained("Wan-AI/Wan2.1-T2V-1.3B-Diffusers", subfolder="transformer", torch_dtype=torch.bfloat16)
-```
-
-## WanTransformer3DModel
-
-[[autodoc]] WanTransformer3DModel
-
-## Transformer2DModelOutput
-
-[[autodoc]] models.modeling_outputs.Transformer2DModelOutput

docs/source/en/api/normalization.md

@@ -29,43 +29,3 @@ Customized normalization layers for supporting various models in 🤗 Diffusers.
 ## AdaGroupNorm
 
 [[autodoc]] models.normalization.AdaGroupNorm
-
-## AdaLayerNormContinuous
-
-[[autodoc]] models.normalization.AdaLayerNormContinuous
-
-## RMSNorm
-
-[[autodoc]] models.normalization.RMSNorm
-
-## GlobalResponseNorm
-
-[[autodoc]] models.normalization.GlobalResponseNorm
-
-
-## LuminaLayerNormContinuous
-[[autodoc]] models.normalization.LuminaLayerNormContinuous
-
-## SD35AdaLayerNormZeroX
-[[autodoc]] models.normalization.SD35AdaLayerNormZeroX
-
-## AdaLayerNormZeroSingle
-[[autodoc]] models.normalization.AdaLayerNormZeroSingle
-
-## LuminaRMSNormZero
-[[autodoc]] models.normalization.LuminaRMSNormZero
-
-## LpNorm
-[[autodoc]] models.normalization.LpNorm
-
-## CogView3PlusAdaLayerNormZeroTextImage
-[[autodoc]] models.normalization.CogView3PlusAdaLayerNormZeroTextImage
-
-## CogVideoXLayerNormZero
-[[autodoc]] models.normalization.CogVideoXLayerNormZero
-
-## MochiRMSNormZero
-[[autodoc]] models.transformers.transformer_mochi.MochiRMSNormZero
-
-## MochiRMSNorm
-[[autodoc]] models.normalization.MochiRMSNorm

docs/source/en/api/pipelines/allegro.md

@@ -19,55 +19,10 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`AllegroPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, AllegroTransformer3DModel, AllegroPipeline
-from diffusers.utils import export_to_video
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "rhymes-ai/Allegro",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = AllegroTransformer3DModel.from_pretrained(
-    "rhymes-ai/Allegro",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = AllegroPipeline.from_pretrained(
-    "rhymes-ai/Allegro",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = (
-    "A seaside harbor with bright sunlight and sparkling seawater, with many boats in the water. From an aerial view, "
-    "the boats vary in size and color, some moving and some stationary. Fishing boats in the water suggest that this "
-    "location might be a popular spot for docking fishing boats."
-)
-video = pipeline(prompt, guidance_scale=7.5, max_sequence_length=512).frames[0]
-export_to_video(video, "harbor.mp4", fps=15)
-```
-
 ## AllegroPipeline
 
 [[autodoc]] AllegroPipeline

docs/source/en/api/pipelines/amused.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 aMUSEd was introduced in [aMUSEd: An Open MUSE Reproduction](https://huggingface.co/papers/2401.01808) by Suraj Patil, William Berman, Robin Rombach, and Patrick von Platen.
 
-Amused is a lightweight text to image model based off of the [MUSE](https://huggingface.co/papers/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
+Amused is a lightweight text to image model based off of the [MUSE](https://arxiv.org/abs/2301.00704) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
 
 Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.
 

docs/source/en/api/pipelines/animatediff.md

@@ -12,13 +12,9 @@ specific language governing permissions and limitations under the License.
 
 # Text-to-Video Generation with AnimateDiff
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 ## Overview
 
-[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://huggingface.co/papers/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
+[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://arxiv.org/abs/2307.04725) by Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai.
 
 The abstract of the paper is the following:
 
@@ -187,7 +183,7 @@ Here are some sample outputs:
 
 ### AnimateDiffSparseControlNetPipeline
 
-[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://huggingface.co/papers/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
+[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) for achieving controlled generation in text-to-video diffusion models by Yuwei Guo, Ceyuan Yang, Anyi Rao, Maneesh Agrawala, Dahua Lin, and Bo Dai.
 
 The abstract from the paper is:
 
@@ -751,7 +747,7 @@ export_to_gif(frames, "animation.gif")
 
 ## Using FreeInit
 
-[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://huggingface.co/papers/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
+[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://arxiv.org/abs/2312.07537) by Tianxing Wu, Chenyang Si, Yuming Jiang, Ziqi Huang, Ziwei Liu.
 
 FreeInit is an effective method that improves temporal consistency and overall quality of videos generated using video-diffusion-models without any addition training. It can be applied to AnimateDiff, ModelScope, VideoCrafter and various other video generation models seamlessly at inference time, and works by iteratively refining the latent-initialization noise. More details can be found it the paper.
 
@@ -807,7 +803,7 @@ FreeInit is not really free - the improved quality comes at the cost of extra co
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -920,7 +916,7 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
 
 ## Using FreeNoise
 
-[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://huggingface.co/papers/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
+[FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://arxiv.org/abs/2310.15169) by Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, Ziwei Liu.
 
 FreeNoise is a sampling mechanism that can generate longer videos with short-video generation models by employing noise-rescheduling, temporal attention over sliding windows, and weighted averaging of latent frames. It also can be used with multiple prompts to allow for interpolated video generations. More details are available in the paper.
 
@@ -966,7 +962,7 @@ pipe.to("cuda")
 prompt = {
     0: "A caterpillar on a leaf, high quality, photorealistic",
     40: "A caterpillar transforming into a cocoon, on a leaf, near flowers, photorealistic",
-    80: "A cocoon on a leaf, flowers in the background, photorealistic",
+    80: "A cocoon on a leaf, flowers in the backgrond, photorealistic",
     120: "A cocoon maturing and a butterfly being born, flowers and leaves visible in the background, photorealistic",
     160: "A beautiful butterfly, vibrant colors, sitting on a leaf, flowers in the background, photorealistic",
     200: "A beautiful butterfly, flying away in a forest, photorealistic",

docs/source/en/api/pipelines/attend_and_excite.md

@@ -22,7 +22,7 @@ You can find additional information about Attend-and-Excite on the [project page
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/audioldm.md

@@ -37,7 +37,7 @@ During inference:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/audioldm2.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AudioLDM 2
 
-AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://huggingface.co/papers/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
+AudioLDM 2 was proposed in [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://arxiv.org/abs/2308.05734) by Haohe Liu et al. AudioLDM 2 takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.
 
 Inspired by [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview), AudioLDM 2 is a text-to-audio _latent diffusion model (LDM)_ that learns continuous audio representations from text embeddings. Two text encoder models are used to compute the text embeddings from a prompt input: the text-branch of [CLAP](https://huggingface.co/docs/transformers/main/en/model_doc/clap) and the encoder of [Flan-T5](https://huggingface.co/docs/transformers/main/en/model_doc/flan-t5). These text embeddings are then projected to a shared embedding space by an [AudioLDM2ProjectionModel](https://huggingface.co/docs/diffusers/main/api/pipelines/audioldm2#diffusers.AudioLDM2ProjectionModel). A [GPT2](https://huggingface.co/docs/transformers/main/en/model_doc/gpt2) _language model (LM)_ is used to auto-regressively predict eight new embedding vectors, conditional on the projected CLAP and Flan-T5 embeddings. The generated embedding vectors and Flan-T5 text embeddings are used as cross-attention conditioning in the LDM. The [UNet](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2UNet2DConditionModel) of AudioLDM 2 is unique in the sense that it takes **two** cross-attention embeddings, as opposed to one cross-attention conditioning, as in most other LDMs.
 
@@ -60,7 +60,7 @@ The following example demonstrates how to construct good music and speech genera
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/aura_flow.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # AuraFlow
 
-AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
+AuraFlow is inspired by [Stable Diffusion 3](../pipelines/stable_diffusion/stable_diffusion_3.md) and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the [GenEval](https://github.com/djghosh13/geneval) benchmark.
 
 It was developed by the Fal team and more details about it can be found in [this blog post](https://blog.fal.ai/auraflow/).
 
@@ -22,90 +22,6 @@ AuraFlow can be quite expensive to run on consumer hardware devices. However, yo
 
 </Tip>
 
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`AuraFlowPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, AuraFlowTransformer2DModel, AuraFlowPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "fal/AuraFlow",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = AuraFlowTransformer2DModel.from_pretrained(
-    "fal/AuraFlow",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = AuraFlowPipeline.from_pretrained(
-    "fal/AuraFlow",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt).images[0]
-image.save("auraflow.png")
-```
-
-Loading [GGUF checkpoints](https://huggingface.co/docs/diffusers/quantization/gguf) are also supported:
-
-```py
-import torch
-from diffusers import (
-    AuraFlowPipeline,
-    GGUFQuantizationConfig,
-    AuraFlowTransformer2DModel,
-)
-
-transformer = AuraFlowTransformer2DModel.from_single_file(
-    "https://huggingface.co/city96/AuraFlow-v0.3-gguf/blob/main/aura_flow_0.3-Q2_K.gguf",
-    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-    torch_dtype=torch.bfloat16,
-)
-
-pipeline = AuraFlowPipeline.from_pretrained(
-    "fal/AuraFlow-v0.3",
-    transformer=transformer,
-    torch_dtype=torch.bfloat16,
-)
-
-prompt = "a cute pony in a field of flowers"
-image = pipeline(prompt).images[0]
-image.save("auraflow.png")
-```
-
-## Support for `torch.compile()`
-
-AuraFlow can be compiled with `torch.compile()` to speed up inference latency even for different resolutions. First, install PyTorch nightly following the instructions from [here](https://pytorch.org/). The snippet below shows the changes needed to enable this:
-
-```diff
-+ torch.fx.experimental._config.use_duck_shape = False
-+ pipeline.transformer = torch.compile(
-    pipeline.transformer, fullgraph=True, dynamic=True
-)
-```
-
-Specifying `use_duck_shape` to be `False` instructs the compiler if it should use the same symbolic variable to represent input sizes that are the same. For more details, check out [this comment](https://github.com/huggingface/diffusers/pull/11327#discussion_r2047659790).
-
-This enables from 100% (on low resolutions) to a 30% (on 1536x1536 resolution) speed improvements.
-
-Thanks to [AstraliteHeart](https://github.com/huggingface/diffusers/pull/11297/) who helped us rewrite the [`AuraFlowTransformer2DModel`] class so that the above works for different resolutions ([PR](https://github.com/huggingface/diffusers/pull/11297/)).
-
 ## AuraFlowPipeline
 
 [[autodoc]] AuraFlowPipeline

docs/source/en/api/pipelines/blip_diffusion.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # BLIP-Diffusion
 
-BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://huggingface.co/papers/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation.
+BLIP-Diffusion was proposed in [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://arxiv.org/abs/2305.14720). It enables zero-shot subject-driven generation and control-guided zero-shot generation.
 
 
 The abstract from the paper is:
@@ -25,7 +25,7 @@ The original codebase can be found at [salesforce/LAVIS](https://github.com/sale
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/chroma.md

@@ -1,71 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Chroma
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
-Chroma is a text to image generation model based on Flux.
-
-Original model checkpoints for Chroma can be found [here](https://huggingface.co/lodestones/Chroma).
-
-<Tip>
-
-Chroma can use all the same optimizations as Flux.
-
-</Tip>
-
-## Inference (Single File)
-
-The `ChromaTransformer2DModel` supports loading checkpoints in the original format. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.
-
-The following example demonstrates how to run Chroma from a single file.
-
-Then run the following example
-
-```python
-import torch
-from diffusers import ChromaTransformer2DModel, ChromaPipeline
-from transformers import T5EncoderModel
-
-bfl_repo = "black-forest-labs/FLUX.1-dev"
-dtype = torch.bfloat16
-
-transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v35.safetensors", torch_dtype=dtype)
-
-text_encoder = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype)
-tokenizer = T5Tokenizer.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype)
-
-pipe = ChromaPipeline.from_pretrained(bfl_repo, transformer=transformer, text_encoder=text_encoder, tokenizer=tokenizer, torch_dtype=dtype)
-
-pipe.enable_model_cpu_offload()
-
-prompt = "A cat holding a sign that says hello world"
-image = pipe(
-    prompt,
-    guidance_scale=4.0,
-    output_type="pil",
-    num_inference_steps=26,
-    generator=torch.Generator("cpu").manual_seed(0)
-).images[0]
-
-image.save("image.png")
-```
-
-## ChromaPipeline
-
-[[autodoc]] ChromaPipeline
-	- all
-	- __call__

docs/source/en/api/pipelines/cogvideox.md

@@ -13,181 +13,113 @@
 # limitations under the License.
 -->
 
-<div style="float: right;">
-  <div class="flex flex-wrap space-x-1">
-    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
-      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-    </a>
-  </div>
-</div>
-
 # CogVideoX
 
-[CogVideoX](https://huggingface.co/papers/2408.06072) is a large diffusion transformer model - available in 2B and 5B parameters - designed to generate longer and more consistent videos from text. This model uses a 3D causal variational autoencoder to more efficiently process video data by reducing sequence length (and associated training compute) and preventing flickering in generated videos. An "expert" transformer with adaptive LayerNorm improves alignment between text and video, and 3D full attention helps accurately capture motion and time in generated videos.
+[CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://arxiv.org/abs/2408.06072) from Tsinghua University & ZhipuAI, by Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang.
 
-You can find all the original CogVideoX checkpoints under the [CogVideoX](https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce) collection.
+The abstract from the paper is:
 
-> [!TIP]
-> Click on the CogVideoX models in the right sidebar for more examples of other video generation tasks.
+*We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compresses videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motion. In addition, we develop an effectively text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of CogVideoX-2B is publicly available at https://github.com/THUDM/CogVideo.*
 
-The example below demonstrates how to generate a video optimized for memory or inference speed.
+<Tip>
 
-<hfoptions id="usage">
-<hfoption id="memory">
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
-Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
+</Tip>
 
-The quantized CogVideoX 5B model below requires ~16GB of VRAM.
+This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
 
-```py
+There are three official CogVideoX checkpoints for text-to-video and video-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`THUDM/CogVideoX-2b`](https://huggingface.co/THUDM/CogVideoX-2b) | torch.float16 |
+| [`THUDM/CogVideoX-5b`](https://huggingface.co/THUDM/CogVideoX-5b) | torch.bfloat16 |
+| [`THUDM/CogVideoX1.5-5b`](https://huggingface.co/THUDM/CogVideoX1.5-5b) | torch.bfloat16 |
+
+There are two official CogVideoX checkpoints available for image-to-video.
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`THUDM/CogVideoX-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-5b-I2V) | torch.bfloat16 |
+| [`THUDM/CogVideoX-1.5-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-1.5-5b-I2V) | torch.bfloat16 |
+
+For the CogVideoX 1.5 series:
+- Text-to-video (T2V) works best at a resolution of 1360x768 because it was trained with that specific resolution.
+- Image-to-video (I2V) works for multiple resolutions. The width can vary from 768 to 1360, but the height must be 768. The height/width must be divisible by 16.
+- Both T2V and I2V models support generation with 81 and 161 frames and work best at this value. Exporting videos at 16 FPS is recommended.
+
+There are two official CogVideoX checkpoints that support pose controllable generation (by the [Alibaba-PAI](https://huggingface.co/alibaba-pai) team).
+
+| checkpoints | recommended inference dtype |
+|:---:|:---:|
+| [`alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose) | torch.bfloat16 |
+| [`alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose) | torch.bfloat16 |
+
+## Inference
+
+Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile) to reduce the inference latency.
+
+First, load the pipeline:
+
+```python
 import torch
-from diffusers import CogVideoXPipeline, AutoModel
-from diffusers.quantizers import PipelineQuantizationConfig
-from diffusers.hooks import apply_group_offloading
-from diffusers.utils import export_to_video
-
-# quantize weights to int8 with torchao
-pipeline_quant_config = PipelineQuantizationConfig(
-  quant_backend="torchao",
-  quant_kwargs={"quant_type": "int8wo"},
-  components_to_quantize=["transformer"]
-)
-
-# fp8 layerwise weight-casting
-transformer = AutoModel.from_pretrained(
-    "THUDM/CogVideoX-5b",
-    subfolder="transformer",
-    torch_dtype=torch.bfloat16
-)
-transformer.enable_layerwise_casting(
-    storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
-)
-
-pipeline = CogVideoXPipeline.from_pretrained(
-    "THUDM/CogVideoX-5b",
-    transformer=transformer,
-    quantization_config=pipeline_quant_config,
-    torch_dtype=torch.bfloat16
-)
-pipeline.to("cuda")
-
-# model-offloading
-pipeline.enable_model_cpu_offload()
-
-prompt = """
-A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. 
-The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. 
-Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, 
-with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.
-"""
-
-video = pipeline(
-    prompt=prompt,
-    guidance_scale=6,
-    num_inference_steps=50
-).frames[0]
-export_to_video(video, "output.mp4", fps=8)
+from diffusers import CogVideoXPipeline, CogVideoXImageToVideoPipeline
+from diffusers.utils import export_to_video,load_image
+pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b").to("cuda") # or "THUDM/CogVideoX-2b" 
 ```
 
-</hfoption>
-<hfoption id="inference speed">
+If you are using the image-to-video pipeline, load it as follows:
 
-[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
-
-The average inference time with torch.compile on a 80GB A100 is 76.27 seconds compared to 96.89 seconds for an uncompiled model.
-
-```py
-import torch
-from diffusers import CogVideoXPipeline
-from diffusers.utils import export_to_video
-
-pipeline = CogVideoXPipeline.from_pretrained(
-    "THUDM/CogVideoX-2b",
-    torch_dtype=torch.float16
-).to("cuda")
-
-# torch.compile
-pipeline.transformer.to(memory_format=torch.channels_last)
-pipeline.transformer = torch.compile(
-    pipeline.transformer, mode="max-autotune", fullgraph=True
-)
-
-prompt = """
-A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. 
-The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. 
-Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, 
-with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.
-"""
-
-video = pipeline(
-    prompt=prompt,
-    guidance_scale=6,
-    num_inference_steps=50
-).frames[0]
-export_to_video(video, "output.mp4", fps=8)
+```python
+pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V").to("cuda")
 ```
 
-</hfoption>
-</hfoptions>
+Then change the memory layout of the pipelines `transformer` component to `torch.channels_last`:
 
-## Notes
+```python
+pipe.transformer.to(memory_format=torch.channels_last)
+```
 
-- CogVideoX supports LoRAs with [`~loaders.CogVideoXLoraLoaderMixin.load_lora_weights`].
+Compile the components and run inference:
 
-  <details>
-  <summary>Show example code</summary>
+```python
+pipe.transformer = torch.compile(pipeline.transformer, mode="max-autotune", fullgraph=True)
 
-  ```py
-  import torch
-  from diffusers import CogVideoXPipeline
-  from diffusers.hooks import apply_group_offloading
-  from diffusers.utils import export_to_video
+# CogVideoX works well with long and well-described prompts
+prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."
+video = pipe(prompt=prompt, guidance_scale=6, num_inference_steps=50).frames[0]
+```
 
-  pipeline = CogVideoXPipeline.from_pretrained(
-      "THUDM/CogVideoX-5b",
-      torch_dtype=torch.bfloat16
-  )
-  pipeline.to("cuda")
+The [T2V benchmark](https://gist.github.com/a-r-r-o-w/5183d75e452a368fd17448fcc810bd3f) results on an 80GB A100 machine are:
 
-  # load LoRA weights
-  pipeline.load_lora_weights("finetrainers/CogVideoX-1.5-crush-smol-v0", adapter_name="crush-lora")
-  pipeline.set_adapters("crush-lora", 0.9)
+```
+Without torch.compile(): Average inference time: 96.89 seconds.
+With torch.compile(): Average inference time: 76.27 seconds.
+```
 
-  # model-offloading
-  pipeline.enable_model_cpu_offload()
+### Memory optimization
 
-  prompt = """
-  PIKA_CRUSH A large metal cylinder is seen pressing down on a pile of Oreo cookies, flattening them as if they were under a hydraulic press.
-  """
-  negative_prompt = "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs"
+CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds of video at 8 FPS) with output resolution 720x480 (W x H), which makes it not possible to run on consumer GPUs or free-tier T4 Colab. The following memory optimizations could be used to reduce the memory footprint. For replication, you can refer to [this](https://gist.github.com/a-r-r-o-w/3959a03f15be5c9bd1fe545b09dfcc93) script.
 
-  video = pipeline(
-      prompt=prompt, 
-      negative_prompt=negative_prompt, 
-      num_frames=81, 
-      height=480,
-      width=768,
-      num_inference_steps=50
-  ).frames[0]
-  export_to_video(video, "output.mp4", fps=16)
-  ```
+- `pipe.enable_model_cpu_offload()`:
+  - Without enabling cpu offloading, memory usage is `33 GB`
+  - With enabling cpu offloading, memory usage is `19 GB`
+- `pipe.enable_sequential_cpu_offload()`:
+  - Similar to `enable_model_cpu_offload` but can significantly reduce memory usage at the cost of slow inference
+  - When enabled, memory usage is under `4 GB`
+- `pipe.vae.enable_tiling()`:
+  - With enabling cpu offloading and tiling, memory usage is `11 GB`
+- `pipe.vae.enable_slicing()`
 
-  </details>
+### Quantized inference
 
-- The text-to-video (T2V) checkpoints work best with a resolution of 1360x768 because that was the resolution it was pretrained on.
+[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
 
-- The image-to-video (I2V) checkpoints work with multiple resolutions. The width can vary from 768 to 1360, but the height must be 758. Both height and width must be divisible by 16.
+It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
+- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
+- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
 
-- Both T2V and I2V checkpoints work best with 81 and 161 frames. It is recommended to export the generated video at 16fps.
-
-- Refer to the table below to view memory usage when various memory-saving techniques are enabled.
-
-  | method | memory usage (enabled) | memory usage (disabled) |
-  |---|---|---|
-  | enable_model_cpu_offload | 19GB | 33GB |
-  | enable_sequential_cpu_offload | <4GB | ~33GB (very slow inference speed) |
-  | enable_tiling | 11GB (with enable_model_cpu_offload) | --- |
- 
 ## CogVideoXPipeline
 
 [[autodoc]] CogVideoXPipeline

docs/source/en/api/pipelines/cogview3.md

@@ -23,7 +23,7 @@ The abstract from the paper is:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/cogview4.md

@@ -1,34 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
--->
-
-# CogView4
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
-
-## CogView4Pipeline
-
-[[autodoc]] CogView4Pipeline
-  - all
-  - __call__
-
-## CogView4PipelineOutput
-
-[[autodoc]] pipelines.cogview4.pipeline_output.CogView4PipelineOutput

docs/source/en/api/pipelines/consisid.md

@@ -1,64 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
--->
-
-# ConsisID
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
-[Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://huggingface.co/papers/2411.17440) from Peking University & University of Rochester & etc, by Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.
-
-The abstract from the paper is:
-
-*Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in the literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving Diffusion Transformer (DiT)-based control scheme. To achieve these goals, we propose **ConsisID**, a tuning-free DiT-based controllable IPT2V model to keep human-**id**entity **consis**tent in the generated video. Inspired by prior findings in frequency analysis of vision/diffusion transformers, it employs identity-control signals in the frequency domain, where facial features can be decomposed into low-frequency global features (e.g., profile, proportions) and high-frequency intrinsic features (e.g., identity markers that remain unaffected by pose changes). First, from a low-frequency perspective, we introduce a global facial extractor, which encodes the reference image and facial key points into a latent space, generating features enriched with low-frequency information. These features are then integrated into the shallow layers of the network to alleviate training challenges associated with DiT. Second, from a high-frequency perspective, we design a local facial extractor to capture high-frequency details and inject them into the transformer blocks, enhancing the model's ability to preserve fine-grained features. To leverage the frequency information for identity preservation, we propose a hierarchical training strategy, transforming a vanilla pre-trained video generation model into an IPT2V model. Extensive experiments demonstrate that our frequency-aware heuristic scheme provides an optimal control solution for DiT-based models. Thanks to this scheme, our **ConsisID** achieves excellent results in generating high-quality, identity-preserving videos, making strides towards more effective IPT2V. The model weight of ConsID is publicly available at https://github.com/PKU-YuanGroup/ConsisID.*
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-This pipeline was contributed by [SHYuanBest](https://github.com/SHYuanBest). The original codebase can be found [here](https://github.com/PKU-YuanGroup/ConsisID). The original weights can be found under [hf.co/BestWishYsh](https://huggingface.co/BestWishYsh).
-
-There are two official ConsisID checkpoints for identity-preserving text-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`BestWishYsh/ConsisID-preview`](https://huggingface.co/BestWishYsh/ConsisID-preview) | torch.bfloat16 |
-| [`BestWishYsh/ConsisID-1.5`](https://huggingface.co/BestWishYsh/ConsisID-preview) | torch.bfloat16 |
-
-### Memory optimization
-
-ConsisID requires about 44 GB of GPU memory to decode 49 frames (6 seconds of video at 8 FPS) with output resolution 720x480 (W x H), which makes it not possible to run on consumer GPUs or free-tier T4 Colab. The following memory optimizations could be used to reduce the memory footprint. For replication, you can refer to [this](https://gist.github.com/SHYuanBest/bc4207c36f454f9e969adbb50eaf8258) script.
-
-| Feature (overlay the previous) | Max Memory Allocated | Max Memory Reserved |
-| :----------------------------- | :------------------- | :------------------ |
-| -                              | 37 GB                | 44 GB               |
-| enable_model_cpu_offload       | 22 GB                | 25 GB               |
-| enable_sequential_cpu_offload  | 16 GB                | 22 GB               |
-| vae.enable_slicing             | 16 GB                | 22 GB               |
-| vae.enable_tiling              | 5 GB                 | 7 GB                |
-
-## ConsisIDPipeline
-
-[[autodoc]] ConsisIDPipeline
-
-  - all
-  - __call__
-
-## ConsisIDPipelineOutput
-
-[[autodoc]] pipelines.consisid.pipeline_output.ConsisIDPipelineOutput

docs/source/en/api/pipelines/control_flux_inpaint.md

@@ -1,93 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team, The Black Forest Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# FluxControlInpaint
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
-FluxControlInpaintPipeline is an implementation of Inpainting for Flux.1 Depth/Canny models. It is a pipeline that allows you to inpaint images using the Flux.1 Depth/Canny models. The pipeline takes an image and a mask as input and returns the inpainted image.
-
-FLUX.1 Depth and Canny [dev] is a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. **This is not a ControlNet model**.
-
-| Control type | Developer | Link |
-| -------- | ---------- | ---- |
-| Depth | [Black Forest Labs](https://huggingface.co/black-forest-labs) | [Link](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev) |
-| Canny | [Black Forest Labs](https://huggingface.co/black-forest-labs) | [Link](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) |
-
-
-<Tip>
-
-Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more. For an exhaustive list of resources, check out [this gist](https://gist.github.com/sayakpaul/b664605caf0aa3bf8585ab109dd5ac9c).
-
-</Tip>
-
-```python
-import torch
-from diffusers import FluxControlInpaintPipeline
-from diffusers.models.transformers import FluxTransformer2DModel
-from transformers import T5EncoderModel
-from diffusers.utils import load_image, make_image_grid
-from image_gen_aux import DepthPreprocessor # https://github.com/huggingface/image_gen_aux
-from PIL import Image
-import numpy as np
-
-pipe = FluxControlInpaintPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-Depth-dev",
-    torch_dtype=torch.bfloat16,
-)
-# use following lines if you have GPU constraints
-# ---------------------------------------------------------------
-transformer = FluxTransformer2DModel.from_pretrained(
-    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="transformer", torch_dtype=torch.bfloat16
-)
-text_encoder_2 = T5EncoderModel.from_pretrained(
-    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="text_encoder_2", torch_dtype=torch.bfloat16
-)
-pipe.transformer = transformer
-pipe.text_encoder_2 = text_encoder_2
-pipe.enable_model_cpu_offload()
-# ---------------------------------------------------------------
-pipe.to("cuda")
-
-prompt = "a blue robot singing opera with human-like expressions"
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-head_mask = np.zeros_like(image)
-head_mask[65:580,300:642] = 255
-mask_image = Image.fromarray(head_mask)
-
-processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-control_image = processor(image)[0].convert("RGB")
-
-output = pipe(
-    prompt=prompt,
-    image=image,
-    control_image=control_image,
-    mask_image=mask_image,
-    num_inference_steps=30,
-    strength=0.9,
-    guidance_scale=10.0,
-    generator=torch.Generator().manual_seed(42),
-).images[0]
-make_image_grid([image, control_image, mask_image, output.resize(image.size)], rows=1, cols=4).save("output.png")
-```
-
-## FluxControlInpaintPipeline
-[[autodoc]] FluxControlInpaintPipeline
-	- all
-	- __call__
-
-
-## FluxPipelineOutput
-[[autodoc]] pipelines.flux.pipeline_output.FluxPipelineOutput

docs/source/en/api/pipelines/controlnet.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
 With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
@@ -30,7 +26,7 @@ The original codebase can be found at [lllyasviel/ControlNet](https://github.com
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_flux.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Flux.1
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 FluxControlNetPipeline is an implementation of ControlNet for Flux.1.
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
@@ -46,7 +42,7 @@ XLabs ControlNets are also supported, which was contributed by the [XLabs team](
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_hunyuandit.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Hunyuan-DiT
 
-HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://huggingface.co/papers/2405.08748).
+HunyuanDiTControlNetPipeline is an implementation of ControlNet for [Hunyuan-DiT](https://arxiv.org/abs/2405.08748).
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
@@ -26,7 +26,7 @@ This code is implemented by Tencent Hunyuan Team. You can find pre-trained check
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_sana.md

@@ -1,36 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# ControlNet
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
-ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
-
-With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
-
-The abstract from the paper is:
-
-*We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with "zero convolutions" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.*
-
-This pipeline was contributed by [ishan24](https://huggingface.co/ishan24). ❤️
-The original codebase can be found at [NVlabs/Sana](https://github.com/NVlabs/Sana), and you can find official ControlNet checkpoints on [Efficient-Large-Model's](https://huggingface.co/Efficient-Large-Model) Hub profile.
-
-## SanaControlNetPipeline
-[[autodoc]] SanaControlNetPipeline
-	- all
-	- __call__
-
-## SanaPipelineOutput
-[[autodoc]] pipelines.sana.pipeline_output.SanaPipelineOutput

docs/source/en/api/pipelines/controlnet_sd3.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Stable Diffusion 3
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 StableDiffusion3ControlNetPipeline is an implementation of ControlNet for Stable Diffusion 3.
 
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
@@ -40,7 +36,7 @@ This controlnet code is mainly implemented by [The InstantX Team](https://huggin
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_sdxl.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet with Stable Diffusion XL
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 ControlNet was introduced in [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) by Lvmin Zhang, Anyi Rao, and Maneesh Agrawala.
 
 With a ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
@@ -36,7 +32,7 @@ If you don't see a checkpoint you're interested in, you can train your own SDXL
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnet_union.md

@@ -1,39 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# ControlNetUnion
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
-ControlNetUnionModel is an implementation of ControlNet for Stable Diffusion XL.
-
-The ControlNet model was introduced in [ControlNetPlus](https://github.com/xinsir6/ControlNetPlus) by xinsir6. It supports multiple conditioning inputs without increasing computation.
-
-*We design a new architecture that can support 10+ control types in condition text-to-image generation and can generate high resolution images visually comparable with midjourney. The network is based on the original ControlNet architecture, we propose two new modules to: 1 Extend the original ControlNet to support different image conditions using the same network parameter. 2 Support multiple conditions input without increasing computation offload, which is especially important for designers who want to edit image in detail, different conditions use the same condition encoder, without adding extra computations or parameters.*
-
-
-## StableDiffusionXLControlNetUnionPipeline
-[[autodoc]] StableDiffusionXLControlNetUnionPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLControlNetUnionImg2ImgPipeline
-[[autodoc]] StableDiffusionXLControlNetUnionImg2ImgPipeline
-	- all
-	- __call__
-
-## StableDiffusionXLControlNetUnionInpaintPipeline
-[[autodoc]] StableDiffusionXLControlNetUnionInpaintPipeline
-	- all
-	- __call__

docs/source/en/api/pipelines/controlnetxs.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # ControlNet-XS
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 ControlNet-XS was introduced in [ControlNet-XS](https://vislearn.github.io/ControlNet-XS/) by Denis Zavadski and Carsten Rother. It is based on the observation that the control model in the [original ControlNet](https://huggingface.co/papers/2302.05543) can be made much smaller and still produce good results.
 
 Like the original ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
@@ -30,7 +26,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/controlnetxs_sdxl.md

@@ -32,7 +32,7 @@ This model was contributed by [UmerHA](https://twitter.com/UmerHAdil). ❤️
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/cosmos.md

@@ -1,57 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-# Cosmos
-
-[Cosmos World Foundation Model Platform for Physical AI](https://huggingface.co/papers/2501.03575) by NVIDIA.
-
-*Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make our platform open-source and our models open-weight with permissive licenses available via https://github.com/NVIDIA/Cosmos.*
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## CosmosTextToWorldPipeline
-
-[[autodoc]] CosmosTextToWorldPipeline
-  - all
-  - __call__
-
-## CosmosVideoToWorldPipeline
-
-[[autodoc]] CosmosVideoToWorldPipeline
-  - all
-  - __call__
-
-## Cosmos2TextToImagePipeline
-
-[[autodoc]] Cosmos2TextToImagePipeline
-  - all
-  - __call__
-
-## Cosmos2VideoToWorldPipeline
-
-[[autodoc]] Cosmos2VideoToWorldPipeline
-  - all
-  - __call__
-
-## CosmosPipelineOutput
-
-[[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput
-
-## CosmosImagePipelineOutput
-
-[[autodoc]] pipelines.cosmos.pipeline_output.CosmosImagePipelineOutput

docs/source/en/api/pipelines/dance_diffusion.md

@@ -19,7 +19,7 @@ Dance Diffusion is the first in a suite of generative audio tools for producers
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/ddpm.md

@@ -22,7 +22,7 @@ The original codebase can be found at [hohonathanho/diffusion](https://github.co
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/deepfloyd_if.md

@@ -12,11 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # DeepFloyd IF
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
 ## Overview
 
 DeepFloyd IF is a novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding.
@@ -347,7 +342,7 @@ pipe.to("cuda")
 image = pipe(image=image, prompt="<prompt>", strength=0.3).images
 ```
 
-You can also use [`torch.compile`](../../optimization/fp16#torchcompile). Note that we have not exhaustively tested `torch.compile`
+You can also use [`torch.compile`](../../optimization/torch2.0). Note that we have not exhaustively tested `torch.compile`
 with IF and it might not give expected results.
 
 ```py

docs/source/en/api/pipelines/dit.md

@@ -22,7 +22,7 @@ The original codebase can be found at [facebookresearch/dit](https://github.com/
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/easyanimate.md

@@ -1,88 +0,0 @@
-<!--Copyright 2025 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
--->
-
-# EasyAnimate
-[EasyAnimate](https://github.com/aigc-apps/EasyAnimate) by Alibaba PAI.
-
-The description from it's GitHub page:
-*EasyAnimate is a pipeline based on the transformer architecture, designed for generating AI images and videos, and for training baseline models and Lora models for Diffusion Transformer. We support direct prediction from pre-trained EasyAnimate models, allowing for the generation of videos with various resolutions, approximately 6 seconds in length, at 8fps (EasyAnimateV5.1, 1 to 49 frames). Additionally, users can train their own baseline and Lora models for specific style transformations.*
-
-This pipeline was contributed by [bubbliiiing](https://github.com/bubbliiiing). The original codebase can be found [here](https://huggingface.co/alibaba-pai). The original weights can be found under [hf.co/alibaba-pai](https://huggingface.co/alibaba-pai).
-
-There are two official EasyAnimate checkpoints for text-to-video and video-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`alibaba-pai/EasyAnimateV5.1-12b-zh`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh) | torch.float16 |
-| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
-
-There is one official EasyAnimate checkpoints available for image-to-video and video-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`alibaba-pai/EasyAnimateV5.1-12b-zh-InP`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-InP) | torch.float16 |
-
-There are two official EasyAnimate checkpoints available for control-to-video.
-
-| checkpoints | recommended inference dtype |
-|:---:|:---:|
-| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control) | torch.float16 |
-| [`alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera`](https://huggingface.co/alibaba-pai/EasyAnimateV5.1-12b-zh-Control-Camera) | torch.float16 |
-
-For the EasyAnimateV5.1 series:
-- Text-to-video (T2V) and Image-to-video (I2V) works for multiple resolutions. The width and height can vary from 256 to 1024.
-- Both T2V and I2V models support generation with 1~49 frames and work best at this value. Exporting videos at 8 FPS is recommended.
-
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`EasyAnimatePipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, EasyAnimateTransformer3DModel, EasyAnimatePipeline
-from diffusers.utils import export_to_video
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = EasyAnimateTransformer3DModel.from_pretrained(
-    "alibaba-pai/EasyAnimateV5.1-12b-zh",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = EasyAnimatePipeline.from_pretrained(
-    "alibaba-pai/EasyAnimateV5.1-12b-zh",
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A cat walks on the grass, realistic style."
-negative_prompt = "bad detailed"
-video = pipeline(prompt=prompt, negative_prompt=negative_prompt, num_frames=49, num_inference_steps=30).frames[0]
-export_to_video(video, "cat.mp4", fps=8)
-```
-
-## EasyAnimatePipeline
-
-[[autodoc]] EasyAnimatePipeline
-  - all
-  - __call__
-
-## EasyAnimatePipelineOutput
-
-[[autodoc]] pipelines.easyanimate.pipeline_output.EasyAnimatePipelineOutput

docs/source/en/api/pipelines/flux.md

@@ -12,11 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # Flux
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
 Flux is a series of text-to-image generation models based on diffusion transformers. To know more about Flux, check out the original [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/) by the creators of Flux, Black Forest Labs.
 
 Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux).
@@ -148,35 +143,6 @@ image = pipe(
 image.save("output.png")
 ```
 
-Canny Control is also possible with a LoRA variant of this condition. The usage is as follows:
-
-```python
-# !pip install -U controlnet-aux
-import torch
-from controlnet_aux import CannyDetector
-from diffusers import FluxControlPipeline
-from diffusers.utils import load_image
-
-pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
-pipe.load_lora_weights("black-forest-labs/FLUX.1-Canny-dev-lora")
-
-prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
-control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-processor = CannyDetector()
-control_image = processor(control_image, low_threshold=50, high_threshold=200, detect_resolution=1024, image_resolution=1024)
-
-image = pipe(
-    prompt=prompt,
-    control_image=control_image,
-    height=1024,
-    width=1024,
-    num_inference_steps=50,
-    guidance_scale=30.0,
-).images[0]
-image.save("output.png")
-```
-
 ### Depth Control
 
 **Note:** `black-forest-labs/Flux.1-Depth-dev` is _not_ a ControlNet model. [`ControlNetModel`] models are a separate component from the UNet/Transformer whose residuals are added to the actual underlying model. Depth Control is an alternate architecture that achieves effectively the same results as a ControlNet model would, by using channel-wise concatenation with input control condition and ensuring the transformer learns structure control by following the condition as closely as possible.
@@ -208,36 +174,6 @@ image = pipe(
 image.save("output.png")
 ```
 
-Depth Control is also possible with a LoRA variant of this condition. The usage is as follows:
-
-```python
-# !pip install git+https://github.com/huggingface/image_gen_aux
-import torch
-from diffusers import FluxControlPipeline, FluxTransformer2DModel
-from diffusers.utils import load_image
-from image_gen_aux import DepthPreprocessor
-
-pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
-pipe.load_lora_weights("black-forest-labs/FLUX.1-Depth-dev-lora")
-
-prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
-control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-control_image = processor(control_image)[0].convert("RGB")
-
-image = pipe(
-    prompt=prompt,
-    control_image=control_image,
-    height=1024,
-    width=1024,
-    num_inference_steps=30,
-    guidance_scale=10.0,
-    generator=torch.Generator().manual_seed(42),
-).images[0]
-image.save("output.png")
-```
-
 ### Redux
 
 * Flux Redux pipeline is an adapter for FLUX.1 base models. It can be used with both flux-dev and flux-schnell, for image-to-image generation.
@@ -273,161 +209,7 @@ images = pipe(
 images[0].save("flux-redux.png")
 ```
 
-## Combining Flux Turbo LoRAs with Flux Control, Fill, and Redux
-
-We can combine Flux Turbo LoRAs with Flux Control and other pipelines like Fill and Redux to enable few-steps' inference. The example below shows how to do that for Flux Control LoRA for depth and turbo LoRA from [`ByteDance/Hyper-SD`](https://hf.co/ByteDance/Hyper-SD).
-
-```py
-from diffusers import FluxControlPipeline
-from image_gen_aux import DepthPreprocessor
-from diffusers.utils import load_image
-from huggingface_hub import hf_hub_download
-import torch
-
-control_pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
-control_pipe.load_lora_weights("black-forest-labs/FLUX.1-Depth-dev-lora", adapter_name="depth")
-control_pipe.load_lora_weights(
-    hf_hub_download("ByteDance/Hyper-SD", "Hyper-FLUX.1-dev-8steps-lora.safetensors"), adapter_name="hyper-sd"
-)
-control_pipe.set_adapters(["depth", "hyper-sd"], adapter_weights=[0.85, 0.125])
-control_pipe.enable_model_cpu_offload()
-
-prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
-control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
-
-processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-control_image = processor(control_image)[0].convert("RGB")
-
-image = control_pipe(
-    prompt=prompt,
-    control_image=control_image,
-    height=1024,
-    width=1024,
-    num_inference_steps=8,
-    guidance_scale=10.0,
-    generator=torch.Generator().manual_seed(42),
-).images[0]
-image.save("output.png")
-```
-
-## Note about `unload_lora_weights()` when using Flux LoRAs
-
-When unloading the Control LoRA weights, call `pipe.unload_lora_weights(reset_to_overwritten_params=True)` to reset the `pipe.transformer` completely back to its original form. The resultant pipeline can then be used with methods like [`DiffusionPipeline.from_pipe`]. More details about this argument are available in [this PR](https://github.com/huggingface/diffusers/pull/10397).
-
-## IP-Adapter
-
-<Tip>
-
-Check out [IP-Adapter](../../../using-diffusers/ip_adapter) to learn more about how IP-Adapters work.
-
-</Tip>
-
-An IP-Adapter lets you prompt Flux with images, in addition to the text prompt. This is especially useful when describing complex concepts that are difficult to articulate through text alone and you have reference images.
-
-```python
-import torch
-from diffusers import FluxPipeline
-from diffusers.utils import load_image
-
-pipe = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16
-).to("cuda")
-
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flux_ip_adapter_input.jpg").resize((1024, 1024))
-
-pipe.load_ip_adapter(
-    "XLabs-AI/flux-ip-adapter",
-    weight_name="ip_adapter.safetensors",
-    image_encoder_pretrained_model_name_or_path="openai/clip-vit-large-patch14"
-)
-pipe.set_ip_adapter_scale(1.0)
-
-image = pipe(
-    width=1024,
-    height=1024,
-    prompt="wearing sunglasses",
-    negative_prompt="",
-    true_cfg_scale=4.0,
-    generator=torch.Generator().manual_seed(4444),
-    ip_adapter_image=image,
-).images[0]
-
-image.save('flux_ip_adapter_output.jpg')
-```
-
-<div class="justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flux_ip_adapter_output.jpg"/>
-    <figcaption class="mt-2 text-sm text-center text-gray-500">IP-Adapter examples with prompt "wearing sunglasses"</figcaption>
-</div>
-
-## Optimize
-
-Flux is a very large model and requires ~50GB of RAM/VRAM to load all the modeling components. Enable some of the optimizations below to lower the memory requirements.
-
-### Group offloading
-
-[Group offloading](../../optimization/memory#group-offloading) lowers VRAM usage by offloading groups of internal layers rather than the whole model or weights. You need to use [`~hooks.apply_group_offloading`] on all the model components of a pipeline. The `offload_type` parameter allows you to toggle between block and leaf-level offloading. Setting it to `leaf_level` offloads the lowest leaf-level parameters to the CPU instead of offloading at the module-level.
-
-On CUDA devices that support asynchronous data streaming, set `use_stream=True` to overlap data transfer and computation to accelerate inference.
-
-> [!TIP]
-> It is possible to mix block and leaf-level offloading for different components in a pipeline.
-
-```py
-import torch
-from diffusers import FluxPipeline
-from diffusers.hooks import apply_group_offloading
-
-model_id = "black-forest-labs/FLUX.1-dev"
-dtype = torch.bfloat16
-pipe = FluxPipeline.from_pretrained(
-	model_id,
-	torch_dtype=dtype,
-)
-
-apply_group_offloading(
-    pipe.transformer,
-    offload_type="leaf_level",
-    offload_device=torch.device("cpu"),
-    onload_device=torch.device("cuda"),
-    use_stream=True,
-)
-apply_group_offloading(
-    pipe.text_encoder, 
-    offload_device=torch.device("cpu"),
-    onload_device=torch.device("cuda"),
-    offload_type="leaf_level",
-    use_stream=True,
-)
-apply_group_offloading(
-    pipe.text_encoder_2, 
-    offload_device=torch.device("cpu"),
-    onload_device=torch.device("cuda"),
-    offload_type="leaf_level",
-    use_stream=True,
-)
-apply_group_offloading(
-    pipe.vae, 
-    offload_device=torch.device("cpu"),
-    onload_device=torch.device("cuda"),
-    offload_type="leaf_level",
-    use_stream=True,
-)
-
-prompt="A cat wearing sunglasses and working as a lifeguard at pool."
-
-generator = torch.Generator().manual_seed(181201)
-image = pipe(
-    prompt,
-    width=576,
-    height=1024,
-    num_inference_steps=30,
-    generator=generator
-).images[0]
-image
-```
-
-### Running FP16 inference
+## Running FP16 inference
 
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.
 
@@ -456,46 +238,6 @@ out = pipe(
 out.save("image.png")
 ```
 
-### Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`FluxPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, FluxTransformer2DModel, FluxPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    subfolder="text_encoder_2",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = FluxTransformer2DModel.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    text_encoder_2=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt, guidance_scale=3.5, height=768, width=1360, num_inference_steps=50).images[0]
-image.save("flux.png")
-```
-
 ## Single File Loading for the `FluxTransformer2DModel`
 
 The `FluxTransformer2DModel` supports loading checkpoints in the original format shipped by Black Forest Labs. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.

docs/source/en/api/pipelines/framepack.md

@@ -1,209 +0,0 @@
-<!-- Copyright 2025 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-# Framepack
-
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
-[Packing Input Frame Context in Next-Frame Prediction Models for Video Generation](https://huggingface.co/papers/2504.12626) by Lvmin Zhang and Maneesh Agrawala.
-
-*We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. The FramePack compresses input frames to make the transformer context length a fixed number regardless of the video length. As a result, we are able to process a large number of frames using video diffusion with computation bottleneck similar to image diffusion. This also makes the training video batch sizes significantly higher (batch sizes become comparable to image diffusion training). We also propose an anti-drifting sampling method that generates frames in inverted temporal order with early-established endpoints to avoid exposure bias (error accumulation over iterations). Finally, we show that existing video diffusion models can be finetuned with FramePack, and their visual quality may be improved because the next-frame prediction supports more balanced diffusion schedulers with less extreme flow shift timesteps.*
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## Available models
-
-| Model name | Description |
-|:---|:---|
-- [`lllyasviel/FramePackI2V_HY`](https://huggingface.co/lllyasviel/FramePackI2V_HY) | Trained with the "inverted anti-drifting" strategy as described in the paper. Inference requires setting `sampling_type="inverted_anti_drifting"` when running the pipeline. |
-- [`lllyasviel/FramePack_F1_I2V_HY_20250503`](https://huggingface.co/lllyasviel/FramePack_F1_I2V_HY_20250503) | Trained with a novel anti-drifting strategy but inference is performed in "vanilla" strategy as described in the paper. Inference requires setting `sampling_type="vanilla"` when running the pipeline. |
-
-## Usage
-
-Refer to the pipeline documentation for basic usage examples. The following section contains examples of offloading, different sampling methods, quantization, and more.
-
-### First and last frame to video
-
-The following example shows how to use Framepack with start and end image controls, using the inverted anti-drifiting sampling model.
-
-```python
-import torch
-from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
-from diffusers.utils import export_to_video, load_image
-from transformers import SiglipImageProcessor, SiglipVisionModel
-
-transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
-    "lllyasviel/FramePackI2V_HY", torch_dtype=torch.bfloat16
-)
-feature_extractor = SiglipImageProcessor.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
-)
-image_encoder = SiglipVisionModel.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
-)
-pipe = HunyuanVideoFramepackPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    transformer=transformer,
-    feature_extractor=feature_extractor,
-    image_encoder=image_encoder,
-    torch_dtype=torch.float16,
-)
-
-# Enable memory optimizations
-pipe.enable_model_cpu_offload()
-pipe.vae.enable_tiling()
-
-prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
-first_image = load_image(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png"
-)
-last_image = load_image(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png"
-)
-output = pipe(
-    image=first_image,
-    last_image=last_image,
-    prompt=prompt,
-    height=512,
-    width=512,
-    num_frames=91,
-    num_inference_steps=30,
-    guidance_scale=9.0,
-    generator=torch.Generator().manual_seed(0),
-    sampling_type="inverted_anti_drifting",
-).frames[0]
-export_to_video(output, "output.mp4", fps=30)
-```
-
-### Vanilla sampling
-
-The following example shows how to use Framepack with the F1 model trained with vanilla sampling but new regulation approach for anti-drifting.
-
-```python
-import torch
-from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
-from diffusers.utils import export_to_video, load_image
-from transformers import SiglipImageProcessor, SiglipVisionModel
-
-transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
-    "lllyasviel/FramePack_F1_I2V_HY_20250503", torch_dtype=torch.bfloat16
-)
-feature_extractor = SiglipImageProcessor.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
-)
-image_encoder = SiglipVisionModel.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
-)
-pipe = HunyuanVideoFramepackPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    transformer=transformer,
-    feature_extractor=feature_extractor,
-    image_encoder=image_encoder,
-    torch_dtype=torch.float16,
-)
-
-# Enable memory optimizations
-pipe.enable_model_cpu_offload()
-pipe.vae.enable_tiling()
-
-image = load_image(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png"
-)
-output = pipe(
-    image=image,
-    prompt="A penguin dancing in the snow",
-    height=832,
-    width=480,
-    num_frames=91,
-    num_inference_steps=30,
-    guidance_scale=9.0,
-    generator=torch.Generator().manual_seed(0),
-    sampling_type="vanilla",
-).frames[0]
-export_to_video(output, "output.mp4", fps=30)
-```
-
-### Group offloading
-
-Group offloading ([`~hooks.apply_group_offloading`]) provides aggressive memory optimizations for offloading internal parts of any model to the CPU, with possibly no additional overhead to generation time. If you have very low VRAM available, this approach may be suitable for you depending on the amount of CPU RAM available.
-
-```python
-import torch
-from diffusers import HunyuanVideoFramepackPipeline, HunyuanVideoFramepackTransformer3DModel
-from diffusers.hooks import apply_group_offloading
-from diffusers.utils import export_to_video, load_image
-from transformers import SiglipImageProcessor, SiglipVisionModel
-
-transformer = HunyuanVideoFramepackTransformer3DModel.from_pretrained(
-    "lllyasviel/FramePack_F1_I2V_HY_20250503", torch_dtype=torch.bfloat16
-)
-feature_extractor = SiglipImageProcessor.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="feature_extractor"
-)
-image_encoder = SiglipVisionModel.from_pretrained(
-    "lllyasviel/flux_redux_bfl", subfolder="image_encoder", torch_dtype=torch.float16
-)
-pipe = HunyuanVideoFramepackPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    transformer=transformer,
-    feature_extractor=feature_extractor,
-    image_encoder=image_encoder,
-    torch_dtype=torch.float16,
-)
-
-# Enable group offloading
-onload_device = torch.device("cuda")
-offload_device = torch.device("cpu")
-list(map(
-    lambda x: apply_group_offloading(x, onload_device, offload_device, offload_type="leaf_level", use_stream=True, low_cpu_mem_usage=True),
-    [pipe.text_encoder, pipe.text_encoder_2, pipe.transformer]
-))
-pipe.image_encoder.to(onload_device)
-pipe.vae.to(onload_device)
-pipe.vae.enable_tiling()
-
-image = load_image(
-    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png"
-)
-output = pipe(
-    image=image,
-    prompt="A penguin dancing in the snow",
-    height=832,
-    width=480,
-    num_frames=91,
-    num_inference_steps=30,
-    guidance_scale=9.0,
-    generator=torch.Generator().manual_seed(0),
-    sampling_type="vanilla",
-).frames[0]
-print(f"Max memory: {torch.cuda.max_memory_allocated() / 1024**3:.3f} GB")
-export_to_video(output, "output.mp4", fps=30)
-```
-
-## HunyuanVideoFramepackPipeline
-
-[[autodoc]] HunyuanVideoFramepackPipeline
-  - all
-  - __call__
-
-## HunyuanVideoPipelineOutput
-
-[[autodoc]] pipelines.hunyuan_video.pipeline_output.HunyuanVideoPipelineOutput
-

docs/source/en/api/pipelines/hidream.md

@@ -1,43 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-# HiDreamImage
-
-[HiDream-I1](https://huggingface.co/HiDream-ai) by HiDream.ai
-
-<Tip>
-
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
-
-</Tip>
-
-## Available models
-
-The following models are available for the [`HiDreamImagePipeline`](text-to-image) pipeline:
-
-| Model name | Description |
-|:---|:---|
-| [`HiDream-ai/HiDream-I1-Full`](https://huggingface.co/HiDream-ai/HiDream-I1-Full) | - |
-| [`HiDream-ai/HiDream-I1-Dev`](https://huggingface.co/HiDream-ai/HiDream-I1-Dev) | - |
-| [`HiDream-ai/HiDream-I1-Fast`](https://huggingface.co/HiDream-ai/HiDream-I1-Fast) | - |
-
-## HiDreamImagePipeline
-
-[[autodoc]] HiDreamImagePipeline
-  - all
-  - __call__
-
-## HiDreamImagePipelineOutput
-
-[[autodoc]] pipelines.hidream_image.pipeline_output.HiDreamImagePipelineOutput

docs/source/en/api/pipelines/hunyuan_video.md

@@ -1,188 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-<div style="float: right;">
-  <div class="flex flex-wrap space-x-1">
-    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
-      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-    </a>
-  </div>
-</div>
-
-# HunyuanVideo
-
-[HunyuanVideo](https://huggingface.co/papers/2412.03603) is a 13B parameter diffusion transformer model designed to be competitive with closed-source video foundation models and enable wider community access. This model uses a "dual-stream to single-stream" architecture to separately process the video and text tokens first, before concatenating and feeding them to the transformer to fuse the multimodal information. A pretrained multimodal large language model (MLLM) is used as the encoder because it has better image-text alignment, better image detail description and reasoning, and it can be used as a zero-shot learner if system instructions are added to user prompts. Finally, HunyuanVideo uses a 3D causal variational autoencoder to more efficiently process video data at the original resolution and frame rate.
-
-You can find all the original HunyuanVideo checkpoints under the [Tencent](https://huggingface.co/tencent) organization.
-
-> [!TIP]
-> Click on the HunyuanVideo models in the right sidebar for more examples of video generation tasks.
->
-> The examples below use a checkpoint from [hunyuanvideo-community](https://huggingface.co/hunyuanvideo-community) because the weights are stored in a layout compatible with Diffusers.
-
-The example below demonstrates how to generate a video optimized for memory or inference speed.
-
-<hfoptions id="usage">
-<hfoption id="memory">
-
-Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
-
-The quantized HunyuanVideo model below requires ~14GB of VRAM.
-
-```py
-import torch
-from diffusers import AutoModel, HunyuanVideoPipeline
-from diffusers.quantizers import PipelineQuantizationConfig
-from diffusers.utils import export_to_video
-
-# quantize weights to int4 with bitsandbytes
-pipeline_quant_config = PipelineQuantizationConfig(
-    quant_backend="bitsandbytes_4bit",
-    quant_kwargs={
-      "load_in_4bit": True,
-      "bnb_4bit_quant_type": "nf4",
-      "bnb_4bit_compute_dtype": torch.bfloat16
-      },
-    components_to_quantize=["transformer"]
-)
-
-pipeline = HunyuanVideoPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    quantization_config=pipeline_quant_config,
-    torch_dtype=torch.bfloat16,
-)
-
-# model-offloading and tiling
-pipeline.enable_model_cpu_offload()
-pipeline.vae.enable_tiling()
-
-prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
-video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-export_to_video(video, "output.mp4", fps=15)
-```
-
-</hfoption>
-<hfoption id="inference speed">
-
-[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
-
-```py
-import torch
-from diffusers import AutoModel, HunyuanVideoPipeline
-from diffusers.quantizers import PipelineQuantizationConfig
-from diffusers.utils import export_to_video
-
-# quantize weights to int4 with bitsandbytes
-pipeline_quant_config = PipelineQuantizationConfig(
-    quant_backend="bitsandbytes_4bit",
-    quant_kwargs={
-      "load_in_4bit": True,
-      "bnb_4bit_quant_type": "nf4",
-      "bnb_4bit_compute_dtype": torch.bfloat16
-      },
-    components_to_quantize=["transformer"]
-)
-
-pipeline = HunyuanVideoPipeline.from_pretrained(
-    "hunyuanvideo-community/HunyuanVideo",
-    quantization_config=pipeline_quant_config,
-    torch_dtype=torch.bfloat16,
-)
-
-# model-offloading and tiling
-pipeline.enable_model_cpu_offload()
-pipeline.vae.enable_tiling()
-
-# torch.compile
-pipeline.transformer.to(memory_format=torch.channels_last)
-pipeline.transformer = torch.compile(
-    pipeline.transformer, mode="max-autotune", fullgraph=True
-)
-
-prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
-video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-export_to_video(video, "output.mp4", fps=15)
-```
-
-</hfoption>
-</hfoptions>
-
-## Notes
-
-- HunyuanVideo supports LoRAs with [`~loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights`].
-
-  <details>
-  <summary>Show example code</summary>
-
-  ```py
-  import torch
-  from diffusers import AutoModel, HunyuanVideoPipeline
-  from diffusers.quantizers import PipelineQuantizationConfig
-  from diffusers.utils import export_to_video
-
-  # quantize weights to int4 with bitsandbytes
-  pipeline_quant_config = PipelineQuantizationConfig(
-      quant_backend="bitsandbytes_4bit",
-      quant_kwargs={
-        "load_in_4bit": True,
-        "bnb_4bit_quant_type": "nf4",
-        "bnb_4bit_compute_dtype": torch.bfloat16
-        },
-      components_to_quantize=["transformer"]
-  )
-
-  pipeline = HunyuanVideoPipeline.from_pretrained(
-      "hunyuanvideo-community/HunyuanVideo",
-      quantization_config=pipeline_quant_config,
-      torch_dtype=torch.bfloat16,
-  )
-
-  # load LoRA weights
-  pipeline.load_lora_weights("https://huggingface.co/lucataco/hunyuan-steamboat-willie-10", adapter_name="steamboat-willie")
-  pipeline.set_adapters("steamboat-willie", 0.9)
-
-  # model-offloading and tiling
-  pipeline.enable_model_cpu_offload()
-  pipeline.vae.enable_tiling()
-
-  # use "In the style of SWR" to trigger the LoRA
-  prompt = """
-  In the style of SWR. A black and white animated scene featuring a fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys.
-  """
-  video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
-  export_to_video(video, "output.mp4", fps=15)
-  ```
-
-  </details>
-
-- Refer to the table below for recommended inference values.
-
-  | parameter | recommended value |
-  |---|---|
-  | text encoder dtype | `torch.float16` |
-  | transformer dtype | `torch.bfloat16` |
-  | vae dtype | `torch.float16` |
-  | `num_frames (k)` | 4 * `k` + 1 |
-
-- Try lower `shift` values (`2.0` to `5.0`) for lower resolution videos and higher `shift` values (`7.0` to `12.0`) for higher resolution images.
-
-## HunyuanVideoPipeline
-
-[[autodoc]] HunyuanVideoPipeline
-  - all
-  - __call__
-
-## HunyuanVideoPipelineOutput
-
-[[autodoc]] pipelines.hunyuan_video.pipeline_output.HunyuanVideoPipelineOutput

docs/source/en/api/pipelines/hunyuandit.md

@@ -13,7 +13,7 @@ specific language governing permissions and limitations under the License.
 # Hunyuan-DiT
 ![chinese elements understanding](https://github.com/gnobitab/diffusers-hunyuan/assets/1157982/39b99036-c3cb-4f16-bb1a-40ec25eda573)
 
-[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://huggingface.co/papers/2405.08748) from Tencent Hunyuan.
+[Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://arxiv.org/abs/2405.08748) from Tencent Hunyuan.
 
 The abstract from the paper is:
 
@@ -30,7 +30,7 @@ HunyuanDiT has the following components:
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/i2vgenxl.md

@@ -22,7 +22,7 @@ The original codebase can be found [here](https://github.com/ali-vilab/i2vgen-xl
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines. Also, to know more about reducing the memory usage of this pipeline, refer to the ["Reduce memory usage"] section [here](../../using-diffusers/svd#reduce-memory-usage).
 
 </Tip>
 
@@ -47,7 +47,7 @@ Sample output with I2VGenXL:
 * Unlike SVD, it additionally accepts text prompts as inputs.
 * It can generate higher resolution videos.
 * When using the [`DDIMScheduler`] (which is default for this pipeline), less than 50 steps for inference leads to bad results.
-* This implementation is 1-stage variant of I2VGenXL. The main figure in the [I2VGen-XL](https://huggingface.co/papers/2311.04145) paper shows a 2-stage variant, however, 1-stage variant works well. See [this discussion](https://github.com/huggingface/diffusers/discussions/7952) for more details.
+* This implementation is 1-stage variant of I2VGenXL. The main figure in the [I2VGen-XL](https://arxiv.org/abs/2311.04145) paper shows a 2-stage variant, however, 1-stage variant works well. See [this discussion](https://github.com/huggingface/diffusers/discussions/7952) for more details.
 
 ## I2VGenXLPipeline
 [[autodoc]] I2VGenXLPipeline

docs/source/en/api/pipelines/kandinsky.md

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky3.md

@@ -9,10 +9,6 @@ specific language governing permissions and limitations under the License.
 
 # Kandinsky 3
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 Kandinsky 3 is created by [Vladimir Arkhipkin](https://github.com/oriBetelgeuse),[Anastasia Maltseva](https://github.com/NastyaMittseva),[Igor Pavlov](https://github.com/boomb0om),[Andrei Filatov](https://github.com/anvilarth),[Arseniy Shakhmatov](https://github.com/cene555),[Andrey Kuznetsov](https://github.com/kuznetsoffandrey),[Denis Dimitrov](https://github.com/denndimitrov), [Zein Shaheen](https://github.com/zeinsh)
 
 The description from it's GitHub page:
@@ -36,7 +32,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kandinsky_v22.md

@@ -25,7 +25,7 @@ Check out the [Kandinsky Community](https://huggingface.co/kandinsky-community)
 
 <Tip>
 
-Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/kolors.md

@@ -12,11 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # Kolors: Effective Training of Diffusion Model for Photorealistic Text-to-Image Synthesis
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-  <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-</div>
-
 ![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/kolors/kolors_header_collage.png)
 
 Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by [the Kuaishou Kolors team](https://github.com/Kwai-Kolors/Kolors). Trained on billions of text-image pairs, Kolors exhibits significant advantages over both open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for both Chinese and English characters. Furthermore, Kolors supports both Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content. For more details, please refer to this [technical report](https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf).

docs/source/en/api/pipelines/latent_consistency_models.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # Latent Consistency Models
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 Latent Consistency Models (LCMs) were proposed in [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://huggingface.co/papers/2310.04378) by Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao.
 
 The abstract of the paper is as follows:

docs/source/en/api/pipelines/latent_diffusion.md

@@ -22,7 +22,7 @@ The original codebase can be found at [CompVis/latent-diffusion](https://github.
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-components-across-pipelines) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 

docs/source/en/api/pipelines/latte.md

@@ -16,19 +16,19 @@
 
 ![latte text-to-video](https://github.com/Vchitect/Latte/blob/52bc0029899babbd6e9250384c83d8ed2670ff7a/visuals/latte.gif?raw=true)
 
-[Latte: Latent Diffusion Transformer for Video Generation](https://huggingface.co/papers/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
+[Latte: Latent Diffusion Transformer for Video Generation](https://arxiv.org/abs/2401.03048) from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.
 
 The abstract from the paper is:
 
 *We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.*
 
-**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://huggingface.co/papers/1803.09179), [SkyTimelapse](https://huggingface.co/papers/1709.07592), [UCF101](https://huggingface.co/papers/1212.0402) and [Taichi-HD](https://huggingface.co/papers/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
+**Highlights**: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - [FaceForensics](https://arxiv.org/abs/1803.09179), [SkyTimelapse](https://arxiv.org/abs/1709.07592), [UCF101](https://arxiv.org/abs/1212.0402) and [Taichi-HD](https://arxiv.org/abs/2003.00196). To prepare and download the datasets for evaluation, please refer to [this https URL](https://github.com/Vchitect/Latte/blob/main/docs/datasets_evaluation.md).
 
 This pipeline was contributed by [maxin-cn](https://github.com/maxin-cn). The original codebase can be found [here](https://github.com/Vchitect/Latte). The original weights can be found under [hf.co/maxin-cn](https://huggingface.co/maxin-cn).
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -70,47 +70,6 @@ Without torch.compile(): Average inference time: 16.246 seconds.
 With torch.compile(): Average inference time: 14.573 seconds.
 ```
 
-## Quantization
-
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LattePipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, LatteTransformer3DModel, LattePipeline
-from diffusers.utils import export_to_gif
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "maxin-cn/Latte-1",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = LatteTransformer3DModel.from_pretrained(
-    "maxin-cn/Latte-1",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = LattePipeline.from_pretrained(
-    "maxin-cn/Latte-1",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "A small cactus with a happy face in the Sahara desert."
-video = pipeline(prompt).frames[0]
-export_to_gif(video, "latte.gif")
-```
-
 ## LattePipeline
 
 [[autodoc]] LattePipeline

docs/source/en/api/pipelines/ledits_pp.md

@@ -12,10 +12,6 @@ specific language governing permissions and limitations under the License.
 
 # LEDITS++
 
-<div class="flex flex-wrap space-x-1">
-  <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-</div>
-
 LEDITS++ was proposed in [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://huggingface.co/papers/2311.16711) by Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinário Passos.
 
 The abstract from the paper is:
@@ -29,7 +25,7 @@ You can find additional information about LEDITS++ on the [project page](https:/
 </Tip>
 
 <Tip warning={true}>
-Due to some backward compatibility issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
+Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion.
 This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp).
 </Tip>
 

docs/source/en/api/pipelines/ltx_video.md

@@ -1,414 +0,0 @@
-<!-- Copyright 2024 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License. -->
-
-<div style="float: right;">
-  <div class="flex flex-wrap space-x-1">
-    <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/using_peft_for_inference" target="_blank" rel="noopener">
-      <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
-    </a>
-    <img alt="MPS" src="https://img.shields.io/badge/MPS-000000?style=flat&logo=apple&logoColor=white%22">
-  </div>
-</div>
-
-# LTX-Video
-
-[LTX-Video](https://huggingface.co/Lightricks/LTX-Video) is a diffusion transformer designed for fast and real-time generation of high-resolution videos from text and images. The main feature of LTX-Video is the Video-VAE. The Video-VAE has a higher pixel to latent compression ratio (1:192) which enables more efficient video data processing and faster generation speed. To support and prevent finer details from being lost during generation, the Video-VAE decoder performs the latent to pixel conversion *and* the last denoising step.
-
-You can find all the original LTX-Video checkpoints under the [Lightricks](https://huggingface.co/Lightricks) organization.
-
-> [!TIP]
-> Click on the LTX-Video models in the right sidebar for more examples of other video generation tasks.
-
-The example below demonstrates how to generate a video optimized for memory or inference speed.
-
-<hfoptions id="usage">
-<hfoption id="memory">
-
-Refer to the [Reduce memory usage](../../optimization/memory) guide for more details about the various memory saving techniques.
-
-The LTX-Video model below requires ~10GB of VRAM.
-
-```py
-import torch
-from diffusers import LTXPipeline, AutoModel
-from diffusers.hooks import apply_group_offloading
-from diffusers.utils import export_to_video
-
-# fp8 layerwise weight-casting
-transformer = AutoModel.from_pretrained(
-    "Lightricks/LTX-Video",
-    subfolder="transformer",
-    torch_dtype=torch.bfloat16
-)
-transformer.enable_layerwise_casting(
-    storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
-)
-
-pipeline = LTXPipeline.from_pretrained("Lightricks/LTX-Video", transformer=transformer, torch_dtype=torch.bfloat16)
-
-# group-offloading
-onload_device = torch.device("cuda")
-offload_device = torch.device("cpu")
-pipeline.transformer.enable_group_offload(onload_device=onload_device, offload_device=offload_device, offload_type="leaf_level", use_stream=True)
-apply_group_offloading(pipeline.text_encoder, onload_device=onload_device, offload_type="block_level", num_blocks_per_group=2)
-apply_group_offloading(pipeline.vae, onload_device=onload_device, offload_type="leaf_level")
-
-prompt = """
-A woman with long brown hair and light skin smiles at another woman with long blonde hair.
-The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek.
-The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and 
-natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
-"""
-negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-
-video = pipeline(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    width=768,
-    height=512,
-    num_frames=161,
-    decode_timestep=0.03,
-    decode_noise_scale=0.025,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output.mp4", fps=24)
-```
-
-</hfoption>
-<hfoption id="inference speed">
-
-[Compilation](../../optimization/fp16#torchcompile) is slow the first time but subsequent calls to the pipeline are faster.
-
-```py
-import torch
-from diffusers import LTXPipeline
-from diffusers.utils import export_to_video
-
-pipeline = LTXPipeline.from_pretrained(
-    "Lightricks/LTX-Video", torch_dtype=torch.bfloat16
-)
-
-# torch.compile
-pipeline.transformer.to(memory_format=torch.channels_last)
-pipeline.transformer = torch.compile(
-    pipeline.transformer, mode="max-autotune", fullgraph=True
-)
-
-prompt = """
-A woman with long brown hair and light skin smiles at another woman with long blonde hair.
-The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek.
-The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and 
-natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage
-"""
-negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-
-video = pipeline(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    width=768,
-    height=512,
-    num_frames=161,
-    decode_timestep=0.03,
-    decode_noise_scale=0.025,
-    num_inference_steps=50,
-).frames[0]
-export_to_video(video, "output.mp4", fps=24)
-```
-
-</hfoption>
-</hfoptions>
-
-## Notes
-
-- Refer to the following recommended settings for generation from the [LTX-Video](https://github.com/Lightricks/LTX-Video) repository.
-
-  - The recommended dtype for the transformer, VAE, and text encoder is `torch.bfloat16`. The VAE and text encoder can also be `torch.float32` or `torch.float16`.
-  - For guidance-distilled variants of LTX-Video, set `guidance_scale` to `1.0`. The `guidance_scale` for any other model should be set higher, like `5.0`, for good generation quality.
-  - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set `decode_timestep` to `0.05` and `image_cond_noise_scale` to `0.025`.
-  - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
-
-- LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
-
-  <details>
-  <summary>Show example code</summary>
-
-  ```py
-  import torch
-  from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
-  from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
-  from diffusers.utils import export_to_video, load_video
-
-  pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-dev", torch_dtype=torch.bfloat16)
-  pipeline_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16)
-  pipeline.to("cuda")
-  pipe_upsample.to("cuda")
-  pipeline.vae.enable_tiling()
-
-  def round_to_nearest_resolution_acceptable_by_vae(height, width):
-      height = height - (height % pipeline.vae_temporal_compression_ratio)
-      width = width - (width % pipeline.vae_temporal_compression_ratio)
-      return height, width
-
-  video = load_video(
-      "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4"
-  )[:21]  # only use the first 21 frames as conditioning
-  condition1 = LTXVideoCondition(video=video, frame_index=0)
-
-  prompt = """
-  The video depicts a winding mountain road covered in snow, with a single vehicle 
-  traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. 
-  The landscape is characterized by rugged terrain and a river visible in the distance. 
-  The scene captures the solitude and beauty of a winter drive through a mountainous region.
-  """
-  negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-  expected_height, expected_width = 768, 1152
-  downscale_factor = 2 / 3
-  num_frames = 161
-
-  # 1. Generate video at smaller resolution
-  # Text-only conditioning is also supported without the need to pass `conditions`
-  downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
-  downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
-  latents = pipeline(
-      conditions=[condition1],
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=downscaled_width,
-      height=downscaled_height,
-      num_frames=num_frames,
-      num_inference_steps=30,
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=5.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="latent",
-  ).frames
-
-  # 2. Upscale generated video using latent upsampler with fewer inference steps
-  # The available latent upsampler upscales the height/width by 2x
-  upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
-  upscaled_latents = pipe_upsample(
-      latents=latents,
-      output_type="latent"
-  ).frames
-
-  # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
-  video = pipeline(
-      conditions=[condition1],
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=upscaled_width,
-      height=upscaled_height,
-      num_frames=num_frames,
-      denoise_strength=0.4,  # Effectively, 4 inference steps out of 10
-      num_inference_steps=10,
-      latents=upscaled_latents,
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=5.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="pil",
-  ).frames[0]
-
-  # 4. Downscale the video to the expected resolution
-  video = [frame.resize((expected_width, expected_height)) for frame in video]
-
-  export_to_video(video, "output.mp4", fps=24)
-  ```
-
-  </details>
-
-- LTX-Video 0.9.7 distilled model is guidance and timestep-distilled to speedup generation. It requires `guidance_scale` to be set to `1.0` and `num_inference_steps` should be set between `4` and `10` for good generation quality. You should also use the following custom timesteps for the best results.
-
-  - Base model inference to prepare for upscaling: `[1000, 993, 987, 981, 975, 909, 725, 0.03]`.
-  - Upscaling: `[1000, 909, 725, 421, 0]`.
-
-  <details>
-  <summary>Show example code</summary>
-
-  ```py
-  import torch
-  from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
-  from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
-  from diffusers.utils import export_to_video, load_video
-
-  pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16)
-  pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16)
-  pipeline.to("cuda")
-  pipe_upsample.to("cuda")
-  pipeline.vae.enable_tiling()
-
-  def round_to_nearest_resolution_acceptable_by_vae(height, width):
-      height = height - (height % pipeline.vae_temporal_compression_ratio)
-      width = width - (width % pipeline.vae_temporal_compression_ratio)
-      return height, width
-
-  prompt = """
-  artistic anatomical 3d render, utlra quality, human half full male body with transparent 
-  skin revealing structure instead of organs, muscular, intricate creative patterns, 
-  monochromatic with backlighting, lightning mesh, scientific concept art, blending biology 
-  with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 
-  16K UHD, rich details. camera zooms out in a rotating fashion
-  """
-  negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-  expected_height, expected_width = 768, 1152
-  downscale_factor = 2 / 3
-  num_frames = 161
-
-  # 1. Generate video at smaller resolution
-  downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
-  downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
-  latents = pipeline(
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=downscaled_width,
-      height=downscaled_height,
-      num_frames=num_frames,
-      timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03],
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=1.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="latent",
-  ).frames
-
-  # 2. Upscale generated video using latent upsampler with fewer inference steps
-  # The available latent upsampler upscales the height/width by 2x
-  upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2
-  upscaled_latents = pipe_upsample(
-      latents=latents,
-      adain_factor=1.0,
-      output_type="latent"
-  ).frames
-
-  # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended)
-  video = pipeline(
-      prompt=prompt,
-      negative_prompt=negative_prompt,
-      width=upscaled_width,
-      height=upscaled_height,
-      num_frames=num_frames,
-      denoise_strength=0.999,  # Effectively, 4 inference steps out of 5
-      timesteps=[1000, 909, 725, 421, 0],
-      latents=upscaled_latents,
-      decode_timestep=0.05,
-      decode_noise_scale=0.025,
-      image_cond_noise_scale=0.0,
-      guidance_scale=1.0,
-      guidance_rescale=0.7,
-      generator=torch.Generator().manual_seed(0),
-      output_type="pil",
-  ).frames[0]
-
-  # 4. Downscale the video to the expected resolution
-  video = [frame.resize((expected_width, expected_height)) for frame in video]
-
-  export_to_video(video, "output.mp4", fps=24)
-  ```
-
-  </details>
-
-- LTX-Video supports LoRAs with [`~loaders.LTXVideoLoraLoaderMixin.load_lora_weights`].
-
-  <details>
-  <summary>Show example code</summary>
-
-  ```py
-  import torch
-  from diffusers import LTXConditionPipeline
-  from diffusers.utils import export_to_video, load_image
-
-  pipeline = LTXConditionPipeline.from_pretrained(
-      "Lightricks/LTX-Video-0.9.5", torch_dtype=torch.bfloat16
-  )
-
-  pipeline.load_lora_weights("Lightricks/LTX-Video-Cakeify-LoRA", adapter_name="cakeify")
-  pipeline.set_adapters("cakeify")
-
-  # use "CAKEIFY" to trigger the LoRA
-  prompt = "CAKEIFY a person using a knife to cut a cake shaped like a Pikachu plushie"
-  image = load_image("https://huggingface.co/Lightricks/LTX-Video-Cakeify-LoRA/resolve/main/assets/images/pikachu.png")
-
-  video = pipeline(
-      prompt=prompt,
-      image=image,
-      width=576,
-      height=576,
-      num_frames=161,
-      decode_timestep=0.03,
-      decode_noise_scale=0.025,
-      num_inference_steps=50,
-  ).frames[0]
-  export_to_video(video, "output.mp4", fps=26)
-  ```
-
-  </details>
-
-- LTX-Video supports loading from single files, such as [GGUF checkpoints](../../quantization/gguf), with [`loaders.FromOriginalModelMixin.from_single_file`] or [`loaders.FromSingleFileMixin.from_single_file`].
-
-  <details>
-  <summary>Show example code</summary>
-
-  ```py
-  import torch
-  from diffusers.utils import export_to_video
-  from diffusers import LTXPipeline, AutoModel, GGUFQuantizationConfig
-
-  transformer = AutoModel.from_single_file(
-      "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf"
-      quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
-      torch_dtype=torch.bfloat16
-  )
-  pipeline = LTXPipeline.from_pretrained(
-      "Lightricks/LTX-Video",
-      transformer=transformer,
-      torch_dtype=torch.bfloat16
-  )
-  ```
-
-  </details>
-
-## LTXPipeline
-
-[[autodoc]] LTXPipeline
-  - all
-  - __call__
-
-## LTXImageToVideoPipeline
-
-[[autodoc]] LTXImageToVideoPipeline
-  - all
-  - __call__
-
-## LTXConditionPipeline
-
-[[autodoc]] LTXConditionPipeline
-  - all
-  - __call__
-
-## LTXLatentUpsamplePipeline
-
-[[autodoc]] LTXLatentUpsamplePipeline
-  - all
-  - __call__
-
-## LTXPipelineOutput
-
-[[autodoc]] pipelines.ltx.pipeline_output.LTXPipelineOutput

docs/source/en/api/pipelines/lumina.md

@@ -28,7 +28,7 @@ Lumina-Next has the following components:
 
 ---
 
-[Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://huggingface.co/papers/2405.05945) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
+[Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://arxiv.org/abs/2405.05945) from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.
 
 The abstract from the paper is:
 
@@ -47,7 +47,7 @@ This pipeline was contributed by [PommesPeter](https://github.com/PommesPeter).
 
 <Tip>
 
-Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
+Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.md) to learn how to explore the tradeoff between scheduler speed and quality, and see the [reuse components across pipelines](../../using-diffusers/loading.md#reuse-a-pipeline) section to learn how to efficiently load the same components into multiple pipelines.
 
 </Tip>
 
@@ -58,10 +58,10 @@ Use [`torch.compile`](https://huggingface.co/docs/diffusers/main/en/tutorials/fa
 First, load the pipeline:
 
 ```python
-from diffusers import LuminaPipeline
+from diffusers import LuminaText2ImgPipeline
 import torch
 
-pipeline = LuminaPipeline.from_pretrained(
+pipeline = LuminaText2ImgPipeline.from_pretrained(
 	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
 ).to("cuda")
 ```
@@ -82,49 +82,9 @@ pipeline.vae.decode = torch.compile(pipeline.vae.decode, mode="max-autotune", fu
 image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures").images[0]
 ```
 
-## Quantization
+## LuminaText2ImgPipeline
 
-Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
-
-Refer to the [Quantization](../../quantization/overview) overview to learn more about supported quantization backends and selecting a quantization backend that supports your use case. The example below demonstrates how to load a quantized [`LuminaPipeline`] for inference with bitsandbytes.
-
-```py
-import torch
-from diffusers import BitsAndBytesConfig as DiffusersBitsAndBytesConfig, Transformer2DModel, LuminaPipeline
-from transformers import BitsAndBytesConfig as BitsAndBytesConfig, T5EncoderModel
-
-quant_config = BitsAndBytesConfig(load_in_8bit=True)
-text_encoder_8bit = T5EncoderModel.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    subfolder="text_encoder",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-quant_config = DiffusersBitsAndBytesConfig(load_in_8bit=True)
-transformer_8bit = Transformer2DModel.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    subfolder="transformer",
-    quantization_config=quant_config,
-    torch_dtype=torch.float16,
-)
-
-pipeline = LuminaPipeline.from_pretrained(
-    "Alpha-VLLM/Lumina-Next-SFT-diffusers",
-    text_encoder=text_encoder_8bit,
-    transformer=transformer_8bit,
-    torch_dtype=torch.float16,
-    device_map="balanced",
-)
-
-prompt = "a tiny astronaut hatching from an egg on the moon"
-image = pipeline(prompt).images[0]
-image.save("lumina.png")
-```
-
-## LuminaPipeline
-
-[[autodoc]] LuminaPipeline
+[[autodoc]] LuminaText2ImgPipeline
 	- all
 	- __call__